Add new SentenceTransformer model.

0da87e5 verified 8 months ago

49.3 kB

	---
	language:
	- en
	library_name: sentence-transformers
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- loss:MatryoshkaLoss
	- loss:MultipleNegativesRankingLoss
	base_model: distilbert/distilroberta-base
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	widget:
	- source_sentence: The gate is yellow.
	sentences:
	- A yellow dog is playing in the snow.
	- A turtle walks over the ground.
	- Three men are on stage playing guitars.
	- source_sentence: A woman is reading.
	sentences:
	- A woman is writing something.
	- A tiger walks around aimlessly.
	- Gunmen 'kill 10 tourists' in Kashmir
	- source_sentence: A man jumping rope
	sentences:
	- A man is climbing a rope.
	- Bombings kill 19 people in Iraq
	- Kittens are eating from dishes.
	- source_sentence: A baby is laughing.
	sentences:
	- A baby is crawling happily.
	- Kittens are eating from dishes.
	- SFG meeting reviews situation in Mali
	- source_sentence: A man shoots a man.
	sentences:
	- A man is shooting off guns.
	- A man is erasing a chalk board.
	- A girl is riding a bicycle.
	pipeline_tag: sentence-similarity
	co2_eq_emissions:
	emissions: 134.46101750442273
	energy_consumed: 0.34592314293320514
	source: codecarbon
	training_type: fine-tuning
	on_cloud: false
	cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
	ram_total_size: 31.777088165283203
	hours_used: 1.296
	hardware_used: 1 x NVIDIA GeForce RTX 3090
	model-index:
	- name: SentenceTransformer based on distilbert/distilroberta-base
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 768
	type: sts-dev-768
	metrics:
	- type: pearson_cosine
	value: 0.8481251400932781
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.851870210632031
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8393267568646925
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8384807951588668
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8409860761844343
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8402437232149903
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.778375740024104
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7779671330832745
	name: Spearman Dot
	- type: pearson_max
	value: 0.8481251400932781
	name: Pearson Max
	- type: spearman_max
	value: 0.851870210632031
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 512
	type: sts-dev-512
	metrics:
	- type: pearson_cosine
	value: 0.8481027005283404
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8523762836460506
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8386304289845581
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8377488866945335
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8402060724091132
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8394674780683281
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7711669414347555
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7713442697629354
	name: Spearman Dot
	- type: pearson_max
	value: 0.8481027005283404
	name: Pearson Max
	- type: spearman_max
	value: 0.8523762836460506
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 256
	type: sts-dev-256
	metrics:
	- type: pearson_cosine
	value: 0.842129976172463
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8488334736505414
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8313278330554295
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8315716535622544
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8333448222091957
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8335338271135746
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7445817504026263
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7450058498333884
	name: Spearman Dot
	- type: pearson_max
	value: 0.842129976172463
	name: Pearson Max
	- type: spearman_max
	value: 0.8488334736505414
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 128
	type: sts-dev-128
	metrics:
	- type: pearson_cosine
	value: 0.8346971467711455
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8445473333837453
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8240728025222037
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8248062249521573
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8254381823447683
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8261820268848477
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7083986436033697
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7093343189476312
	name: Spearman Dot
	- type: pearson_max
	value: 0.8346971467711455
	name: Pearson Max
	- type: spearman_max
	value: 0.8445473333837453
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 64
	type: sts-dev-64
	metrics:
	- type: pearson_cosine
	value: 0.8201235619233855
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8352180907883887
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8032422421113089
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8047180797117756
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8059536263441476
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8072309964597537
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.6360301824635421
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6388601952951507
	name: Spearman Dot
	- type: pearson_max
	value: 0.8201235619233855
	name: Pearson Max
	- type: spearman_max
	value: 0.8352180907883887
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 768
	type: sts-test-768
	metrics:
	- type: pearson_cosine
	value: 0.8262197279185375
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8297611922199533
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8103738584802076
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8032653500693283
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8113711464219397
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8047844488402207
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7351063083543349
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7222898603318773
	name: Spearman Dot
	- type: pearson_max
	value: 0.8262197279185375
	name: Pearson Max
	- type: spearman_max
	value: 0.8297611922199533
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 512
	type: sts-test-512
	metrics:
	- type: pearson_cosine
	value: 0.8265289700873992
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8303420710627304
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8092042518460232
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8021561300791633
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8099517575676378
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8034311442407586
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7239156858292818
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7141021600172974
	name: Spearman Dot
	- type: pearson_max
	value: 0.8265289700873992
	name: Pearson Max
	- type: spearman_max
	value: 0.8303420710627304
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 256
	type: sts-test-256
	metrics:
	- type: pearson_cosine
	value: 0.8247713863827557
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8304669772286988
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8012313573943666
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7951476656544464
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8028104839960224
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7974260171623634
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7011271518071694
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6946104528279369
	name: Spearman Dot
	- type: pearson_max
	value: 0.8247713863827557
	name: Pearson Max
	- type: spearman_max
	value: 0.8304669772286988
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 128
	type: sts-test-128
	metrics:
	- type: pearson_cosine
	value: 0.8205553018873636
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8283987535951244
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7931877193499666
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7878356187942884
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7946730313407452
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7891423743206649
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.6617612604436709
	name: Pearson Dot
	- type: spearman_dot
	value: 0.658567255717814
	name: Spearman Dot
	- type: pearson_max
	value: 0.8205553018873636
	name: Pearson Max
	- type: spearman_max
	value: 0.8283987535951244
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 64
	type: sts-test-64
	metrics:
	- type: pearson_cosine
	value: 0.8118818737650724
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8241392189948019
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7761319753952881
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7738169467058665
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7777045912119006
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7745630850628562
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5934162536230442
	name: Pearson Dot
	- type: spearman_dot
	value: 0.5884207612393454
	name: Spearman Dot
	- type: pearson_max
	value: 0.8118818737650724
	name: Pearson Max
	- type: spearman_max
	value: 0.8241392189948019
	name: Spearman Max
	---

	# SentenceTransformer based on distilbert/distilroberta-base

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. It maps sentences & paragraphs to a 768-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: [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
	- 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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
	(1): Pooling({'word_embedding_dimension': 768, '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})
	)
	```

	## 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("tomaarsen/distilroberta-base-nli-matryoshka-v3")
	# Run inference
	sentences = [
	'A man shoots a man.',
	'A man is shooting off guns.',
	'A man is erasing a chalk board.',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(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

	#### Semantic Similarity
	* Dataset: `sts-dev-768`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8481 \|
	\| spearman_cosine \| 0.8519 \|
	\| pearson_manhattan \| 0.8393 \|
	\| spearman_manhattan \| 0.8385 \|
	\| pearson_euclidean \| 0.841 \|
	\| spearman_euclidean \| 0.8402 \|
	\| pearson_dot \| 0.7784 \|
	\| spearman_dot \| 0.778 \|
	\| pearson_max \| 0.8481 \|
	\| spearman_max \| 0.8519 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-512`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8481 \|
	\| spearman_cosine \| 0.8524 \|
	\| pearson_manhattan \| 0.8386 \|
	\| spearman_manhattan \| 0.8377 \|
	\| pearson_euclidean \| 0.8402 \|
	\| spearman_euclidean \| 0.8395 \|
	\| pearson_dot \| 0.7712 \|
	\| spearman_dot \| 0.7713 \|
	\| pearson_max \| 0.8481 \|
	\| spearman_max \| 0.8524 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-256`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8421 \|
	\| spearman_cosine \| 0.8488 \|
	\| pearson_manhattan \| 0.8313 \|
	\| spearman_manhattan \| 0.8316 \|
	\| pearson_euclidean \| 0.8333 \|
	\| spearman_euclidean \| 0.8335 \|
	\| pearson_dot \| 0.7446 \|
	\| spearman_dot \| 0.745 \|
	\| pearson_max \| 0.8421 \|
	\| spearman_max \| 0.8488 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-128`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8347 \|
	\| spearman_cosine \| 0.8445 \|
	\| pearson_manhattan \| 0.8241 \|
	\| spearman_manhattan \| 0.8248 \|
	\| pearson_euclidean \| 0.8254 \|
	\| spearman_euclidean \| 0.8262 \|
	\| pearson_dot \| 0.7084 \|
	\| spearman_dot \| 0.7093 \|
	\| pearson_max \| 0.8347 \|
	\| spearman_max \| 0.8445 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-64`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8201 \|
	\| spearman_cosine \| 0.8352 \|
	\| pearson_manhattan \| 0.8032 \|
	\| spearman_manhattan \| 0.8047 \|
	\| pearson_euclidean \| 0.806 \|
	\| spearman_euclidean \| 0.8072 \|
	\| pearson_dot \| 0.636 \|
	\| spearman_dot \| 0.6389 \|
	\| pearson_max \| 0.8201 \|
	\| spearman_max \| 0.8352 \|

	#### Semantic Similarity
	* Dataset: `sts-test-768`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8262 \|
	\| spearman_cosine \| 0.8298 \|
	\| pearson_manhattan \| 0.8104 \|
	\| spearman_manhattan \| 0.8033 \|
	\| pearson_euclidean \| 0.8114 \|
	\| spearman_euclidean \| 0.8048 \|
	\| pearson_dot \| 0.7351 \|
	\| spearman_dot \| 0.7223 \|
	\| pearson_max \| 0.8262 \|
	\| spearman_max \| 0.8298 \|

	#### Semantic Similarity
	* Dataset: `sts-test-512`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8265 \|
	\| spearman_cosine \| 0.8303 \|
	\| pearson_manhattan \| 0.8092 \|
	\| spearman_manhattan \| 0.8022 \|
	\| pearson_euclidean \| 0.81 \|
	\| spearman_euclidean \| 0.8034 \|
	\| pearson_dot \| 0.7239 \|
	\| spearman_dot \| 0.7141 \|
	\| pearson_max \| 0.8265 \|
	\| spearman_max \| 0.8303 \|

	#### Semantic Similarity
	* Dataset: `sts-test-256`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8248 \|
	\| spearman_cosine \| 0.8305 \|
	\| pearson_manhattan \| 0.8012 \|
	\| spearman_manhattan \| 0.7951 \|
	\| pearson_euclidean \| 0.8028 \|
	\| spearman_euclidean \| 0.7974 \|
	\| pearson_dot \| 0.7011 \|
	\| spearman_dot \| 0.6946 \|
	\| pearson_max \| 0.8248 \|
	\| spearman_max \| 0.8305 \|

	#### Semantic Similarity
	* Dataset: `sts-test-128`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8206 \|
	\| spearman_cosine \| 0.8284 \|
	\| pearson_manhattan \| 0.7932 \|
	\| spearman_manhattan \| 0.7878 \|
	\| pearson_euclidean \| 0.7947 \|
	\| spearman_euclidean \| 0.7891 \|
	\| pearson_dot \| 0.6618 \|
	\| spearman_dot \| 0.6586 \|
	\| pearson_max \| 0.8206 \|
	\| spearman_max \| 0.8284 \|

	#### Semantic Similarity
	* Dataset: `sts-test-64`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8119 \|
	\| spearman_cosine \| 0.8241 \|
	\| pearson_manhattan \| 0.7761 \|
	\| spearman_manhattan \| 0.7738 \|
	\| pearson_euclidean \| 0.7777 \|
	\| spearman_euclidean \| 0.7746 \|
	\| pearson_dot \| 0.5934 \|
	\| spearman_dot \| 0.5884 \|
	\| pearson_max \| 0.8119 \|
	\| spearman_max \| 0.8241 \|

	<!--
	## 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

	#### sentence-transformers/all-nli

	* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [65dd388](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/65dd38867b600f42241d2066ba1a35fbd097fcfe)
	* Size: 557,850 training samples
	* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| anchor \| positive \| negative \|
	\|:--------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|
	\| type \| string \| string \| string \|
	\| details \| <ul><li>min: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \| negative \|
	\|:---------------------------------------------------------------------------\|:-------------------------------------------------\|:-----------------------------------------------------------\|
	\| <code>A person on a horse jumps over a broken down airplane.</code> \| <code>A person is outdoors, on a horse.</code> \| <code>A person is at a diner, ordering an omelette.</code> \|
	\| <code>Children smiling and waving at camera</code> \| <code>There are children present</code> \| <code>The kids are frowning</code> \|
	\| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> \| <code>The boy does a skateboarding trick.</code> \| <code>The boy skates down the sidewalk.</code> \|
	* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/losses.html#matryoshkaloss) with these parameters:
	```json
	{
	"loss": "MultipleNegativesRankingLoss",
	"matryoshka_dims": [
	768,
	512,
	256,
	128,
	64
	],
	"matryoshka_weights": [
	1,
	1,
	1,
	1,
	1
	],
	"n_dims_per_step": -1
	}
	```

	### Evaluation Dataset

	#### sentence-transformers/stsb

	* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
	* Size: 1,500 evaluation samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| score \|
	\|:--------\|:---------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 5 tokens</li><li>mean: 15.0 tokens</li><li>max: 44 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 14.99 tokens</li><li>max: 61 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| score \|
	\|:--------------------------------------------------\|:------------------------------------------------------\|:------------------\|
	\| <code>A man with a hard hat is dancing.</code> \| <code>A man wearing a hard hat is dancing.</code> \| <code>1.0</code> \|
	\| <code>A young child is riding a horse.</code> \| <code>A child is riding a horse.</code> \| <code>0.95</code> \|
	\| <code>A man is feeding a mouse to a snake.</code> \| <code>The man is feeding a mouse to the snake.</code> \| <code>1.0</code> \|
	* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/losses.html#matryoshkaloss) with these parameters:
	```json
	{
	"loss": "MultipleNegativesRankingLoss",
	"matryoshka_dims": [
	768,
	512,
	256,
	128,
	64
	],
	"matryoshka_weights": [
	1,
	1,
	1,
	1,
	1
	],
	"n_dims_per_step": -1
	}
	```

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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 128
	- `per_device_eval_batch_size`: 128
	- `num_train_epochs`: 1
	- `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`: False
	- `per_device_train_batch_size`: 128
	- `per_device_eval_batch_size`: 128
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `learning_rate`: 5e-05
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 1
	- `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
	- `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`: None
	- `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_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| sts-dev-128_spearman_cosine \| sts-dev-256_spearman_cosine \| sts-dev-512_spearman_cosine \| sts-dev-64_spearman_cosine \| sts-dev-768_spearman_cosine \| sts-test-128_spearman_cosine \| sts-test-256_spearman_cosine \| sts-test-512_spearman_cosine \| sts-test-64_spearman_cosine \| sts-test-768_spearman_cosine \|
	\|:------:\|:----:\|:-------------:\|:-------:\|:---------------------------:\|:---------------------------:\|:---------------------------:\|:--------------------------:\|:---------------------------:\|:----------------------------:\|:----------------------------:\|:----------------------------:\|:---------------------------:\|:----------------------------:\|
	\| 0.0229 \| 100 \| 19.9245 \| 11.3900 \| 0.7772 \| 0.7998 \| 0.8049 \| 0.7902 \| 0.7919 \| - \| - \| - \| - \| - \|
	\| 0.0459 \| 200 \| 10.6055 \| 11.1510 \| 0.7809 \| 0.7996 \| 0.8055 \| 0.7954 \| 0.7954 \| - \| - \| - \| - \| - \|
	\| 0.0688 \| 300 \| 9.6389 \| 11.1229 \| 0.7836 \| 0.8029 \| 0.8114 \| 0.7923 \| 0.8083 \| - \| - \| - \| - \| - \|
	\| 0.0918 \| 400 \| 8.6917 \| 11.0299 \| 0.7976 \| 0.8117 \| 0.8142 \| 0.8002 \| 0.8087 \| - \| - \| - \| - \| - \|
	\| 0.1147 \| 500 \| 8.3064 \| 11.3586 \| 0.7895 \| 0.8058 \| 0.8120 \| 0.7978 \| 0.8065 \| - \| - \| - \| - \| - \|
	\| 0.1376 \| 600 \| 7.8026 \| 11.5047 \| 0.7876 \| 0.8015 \| 0.8065 \| 0.7934 \| 0.8016 \| - \| - \| - \| - \| - \|
	\| 0.1606 \| 700 \| 7.9978 \| 11.5823 \| 0.7944 \| 0.8067 \| 0.8072 \| 0.7994 \| 0.8045 \| - \| - \| - \| - \| - \|
	\| 0.1835 \| 800 \| 6.9249 \| 11.5862 \| 0.7945 \| 0.8054 \| 0.8085 \| 0.8012 \| 0.8033 \| - \| - \| - \| - \| - \|
	\| 0.2065 \| 900 \| 7.1059 \| 11.2365 \| 0.7895 \| 0.8035 \| 0.8072 \| 0.7956 \| 0.8031 \| - \| - \| - \| - \| - \|
	\| 0.2294 \| 1000 \| 6.5483 \| 11.3770 \| 0.7853 \| 0.7994 \| 0.8039 \| 0.7894 \| 0.8024 \| - \| - \| - \| - \| - \|
	\| 0.2524 \| 1100 \| 6.6684 \| 11.5038 \| 0.7968 \| 0.8087 \| 0.8115 \| 0.8002 \| 0.8065 \| - \| - \| - \| - \| - \|
	\| 0.2753 \| 1200 \| 6.4661 \| 11.4057 \| 0.7980 \| 0.8082 \| 0.8103 \| 0.8057 \| 0.8070 \| - \| - \| - \| - \| - \|
	\| 0.2982 \| 1300 \| 6.501 \| 11.2521 \| 0.7974 \| 0.8100 \| 0.8111 \| 0.8025 \| 0.8079 \| - \| - \| - \| - \| - \|
	\| 0.3212 \| 1400 \| 6.0769 \| 11.1458 \| 0.7971 \| 0.8103 \| 0.8124 \| 0.7982 \| 0.8082 \| - \| - \| - \| - \| - \|
	\| 0.3441 \| 1500 \| 6.1919 \| 11.3180 \| 0.8039 \| 0.8129 \| 0.8144 \| 0.8094 \| 0.8098 \| - \| - \| - \| - \| - \|
	\| 0.3671 \| 1600 \| 5.8213 \| 11.6196 \| 0.7924 \| 0.8072 \| 0.8090 \| 0.8003 \| 0.8012 \| - \| - \| - \| - \| - \|
	\| 0.3900 \| 1700 \| 5.534 \| 11.0700 \| 0.7979 \| 0.8104 \| 0.8132 \| 0.8028 \| 0.8101 \| - \| - \| - \| - \| - \|
	\| 0.4129 \| 1800 \| 5.7536 \| 11.0916 \| 0.7934 \| 0.8087 \| 0.8149 \| 0.8008 \| 0.8085 \| - \| - \| - \| - \| - \|
	\| 0.4359 \| 1900 \| 5.3778 \| 11.2658 \| 0.7942 \| 0.8084 \| 0.8104 \| 0.7980 \| 0.8049 \| - \| - \| - \| - \| - \|
	\| 0.4588 \| 2000 \| 5.4925 \| 11.4851 \| 0.7932 \| 0.8062 \| 0.8086 \| 0.7932 \| 0.8057 \| - \| - \| - \| - \| - \|
	\| 0.4818 \| 2100 \| 5.3125 \| 11.4833 \| 0.7987 \| 0.8119 \| 0.8154 \| 0.8012 \| 0.8124 \| - \| - \| - \| - \| - \|
	\| 0.5047 \| 2200 \| 5.1914 \| 11.2848 \| 0.7784 \| 0.7971 \| 0.8037 \| 0.7911 \| 0.8004 \| - \| - \| - \| - \| - \|
	\| 0.5276 \| 2300 \| 5.2921 \| 11.5364 \| 0.7698 \| 0.7910 \| 0.7974 \| 0.7839 \| 0.7900 \| - \| - \| - \| - \| - \|
	\| 0.5506 \| 2400 \| 5.288 \| 11.3944 \| 0.7873 \| 0.8011 \| 0.8051 \| 0.7877 \| 0.8003 \| - \| - \| - \| - \| - \|
	\| 0.5735 \| 2500 \| 5.3697 \| 11.4532 \| 0.7949 \| 0.8077 \| 0.8111 \| 0.7955 \| 0.8069 \| - \| - \| - \| - \| - \|
	\| 0.5965 \| 2600 \| 5.1521 \| 11.2788 \| 0.7973 \| 0.8095 \| 0.8130 \| 0.7940 \| 0.8088 \| - \| - \| - \| - \| - \|
	\| 0.6194 \| 2700 \| 5.2316 \| 11.2472 \| 0.7948 \| 0.8077 \| 0.8102 \| 0.7939 \| 0.8053 \| - \| - \| - \| - \| - \|
	\| 0.6423 \| 2800 \| 5.2599 \| 11.4171 \| 0.7882 \| 0.8029 \| 0.8065 \| 0.7888 \| 0.8019 \| - \| - \| - \| - \| - \|
	\| 0.6653 \| 2900 \| 5.4052 \| 11.4026 \| 0.7871 \| 0.8005 \| 0.8021 \| 0.7833 \| 0.7985 \| - \| - \| - \| - \| - \|
	\| 0.6882 \| 3000 \| 5.3474 \| 11.2084 \| 0.7895 \| 0.8047 \| 0.8079 \| 0.7928 \| 0.8050 \| - \| - \| - \| - \| - \|
	\| 0.7112 \| 3100 \| 5.0336 \| 11.3999 \| 0.8023 \| 0.8150 \| 0.8182 \| 0.8024 \| 0.8168 \| - \| - \| - \| - \| - \|
	\| 0.7341 \| 3200 \| 5.2496 \| 11.2307 \| 0.8015 \| 0.8137 \| 0.8167 \| 0.8000 \| 0.8140 \| - \| - \| - \| - \| - \|
	\| 0.7571 \| 3300 \| 3.8712 \| 10.9468 \| 0.8396 \| 0.8440 \| 0.8471 \| 0.8284 \| 0.8479 \| - \| - \| - \| - \| - \|
	\| 0.7800 \| 3400 \| 2.7068 \| 10.9292 \| 0.8414 \| 0.8453 \| 0.8489 \| 0.8305 \| 0.8497 \| - \| - \| - \| - \| - \|
	\| 0.8029 \| 3500 \| 2.3418 \| 10.8626 \| 0.8427 \| 0.8467 \| 0.8504 \| 0.8322 \| 0.8504 \| - \| - \| - \| - \| - \|
	\| 0.8259 \| 3600 \| 2.2419 \| 10.9065 \| 0.8421 \| 0.8467 \| 0.8504 \| 0.8320 \| 0.8502 \| - \| - \| - \| - \| - \|
	\| 0.8488 \| 3700 \| 2.125 \| 10.9517 \| 0.8424 \| 0.8472 \| 0.8509 \| 0.8324 \| 0.8510 \| - \| - \| - \| - \| - \|
	\| 0.8718 \| 3800 \| 1.9942 \| 11.0142 \| 0.8438 \| 0.8482 \| 0.8519 \| 0.8337 \| 0.8517 \| - \| - \| - \| - \| - \|
	\| 0.8947 \| 3900 \| 2.031 \| 10.9662 \| 0.8433 \| 0.8480 \| 0.8519 \| 0.8340 \| 0.8515 \| - \| - \| - \| - \| - \|
	\| 0.9176 \| 4000 \| 1.9734 \| 11.0054 \| 0.8452 \| 0.8495 \| 0.8531 \| 0.8354 \| 0.8528 \| - \| - \| - \| - \| - \|
	\| 0.9406 \| 4100 \| 1.9468 \| 11.0183 \| 0.8447 \| 0.8490 \| 0.8526 \| 0.8348 \| 0.8522 \| - \| - \| - \| - \| - \|
	\| 0.9635 \| 4200 \| 1.9008 \| 11.0154 \| 0.8445 \| 0.8485 \| 0.8521 \| 0.8352 \| 0.8517 \| - \| - \| - \| - \| - \|
	\| 0.9865 \| 4300 \| 1.8511 \| 10.9966 \| 0.8445 \| 0.8488 \| 0.8524 \| 0.8352 \| 0.8519 \| - \| - \| - \| - \| - \|
	\| 1.0 \| 4359 \| - \| - \| - \| - \| - \| - \| - \| 0.8284 \| 0.8305 \| 0.8303 \| 0.8241 \| 0.8298 \|


	### Environmental Impact
	Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
	- Energy Consumed: 0.346 kWh
	- Carbon Emitted: 0.134 kg of CO2
	- Hours Used: 1.296 hours

	### Training Hardware
	- On Cloud: No
	- GPU Model: 1 x NVIDIA GeForce RTX 3090
	- CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
	- RAM Size: 31.78 GB

	### Framework Versions
	- Python: 3.11.6
	- Sentence Transformers: 3.0.0.dev0
	- Transformers: 4.41.0.dev0
	- PyTorch: 2.3.0+cu121
	- Accelerate: 0.26.1
	- Datasets: 2.18.0
	- 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",
	}
	```

	#### MatryoshkaLoss
	```bibtex
	@misc{kusupati2024matryoshka,
	title={Matryoshka Representation Learning},
	author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
	year={2024},
	eprint={2205.13147},
	archivePrefix={arXiv},
	primaryClass={cs.LG}
	}
	```

	#### MultipleNegativesRankingLoss
	```bibtex
	@misc{henderson2017efficient,
	title={Efficient Natural Language Response Suggestion for Smart Reply},
	author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
	year={2017},
	eprint={1705.00652},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->