Add new SentenceTransformer model.

282807e verified 6 months ago

49.2 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: A baby is laughing.
	sentences:
	- The baby laughed in his car seat.
	- A toddler walks down a hallway.
	- Japan falls silent to mark 311 tragedy
	- source_sentence: A woman is reading.
	sentences:
	- A woman is writing something.
	- The man is in a deserted field.
	- Obama urges no new sanctions on Iran
	- source_sentence: A man is spitting.
	sentences:
	- A man is crying.
	- A girl plays a wind instrument.
	- Kids playing ball in the park.
	- source_sentence: A man shoots a man.
	sentences:
	- A man is shooting off guns.
	- A slow loris hanging on a cord.
	- Finance minister promises no new taxes
	- source_sentence: A boy is vacuuming.
	sentences:
	- A little boy is vacuuming the floor.
	- A woman is applying eye shadow.
	- Glorious triple-gold night for Britain
	pipeline_tag: sentence-similarity
	co2_eq_emissions:
	emissions: 94.71657156591533
	energy_consumed: 0.2436740010751561
	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: 0.923
	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 256
	type: sts-dev-256
	metrics:
	- type: pearson_cosine
	value: 0.832978199459682
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8449812730792539
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8284059469034439
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8314151253676515
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8291459460248565
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8319080532683886
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7274279213358037
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7358272455513368
	name: Spearman Dot
	- type: pearson_max
	value: 0.832978199459682
	name: Pearson Max
	- type: spearman_max
	value: 0.8449812730792539
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 128
	type: sts-dev-128
	metrics:
	- type: pearson_cosine
	value: 0.8266436609310417
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.841563547795295
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8250171666597236
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8276544602820737
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8255984422889996
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.828520082690129
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7120095981036954
	name: Pearson Dot
	- type: spearman_dot
	value: 0.7163267085950832
	name: Spearman Dot
	- type: pearson_max
	value: 0.8266436609310417
	name: Pearson Max
	- type: spearman_max
	value: 0.841563547795295
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 64
	type: sts-dev-64
	metrics:
	- type: pearson_cosine
	value: 0.817074395539638
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8355573303767316
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8175610864074738
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8212543828500742
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8175058817585
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8216438541895171
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.6852246329807953
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6861394760239012
	name: Spearman Dot
	- type: pearson_max
	value: 0.8175610864074738
	name: Pearson Max
	- type: spearman_max
	value: 0.8355573303767316
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 32
	type: sts-dev-32
	metrics:
	- type: pearson_cosine
	value: 0.7963856490231295
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8243820415687734
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7982768947167747
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.804919985023919
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.800259304954162
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8069660671225415
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.6311831976256888
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6277202377535699
	name: Spearman Dot
	- type: pearson_max
	value: 0.800259304954162
	name: Pearson Max
	- type: spearman_max
	value: 0.8243820415687734
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev 16
	type: sts-dev-16
	metrics:
	- type: pearson_cosine
	value: 0.7401161630034654
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.7871969780219474
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7609788932639057
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7761115272699121
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7645256699036285
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7794348361665424
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5201701018366058
	name: Pearson Dot
	- type: spearman_dot
	value: 0.511537896780009
	name: Spearman Dot
	- type: pearson_max
	value: 0.7645256699036285
	name: Pearson Max
	- type: spearman_max
	value: 0.7871969780219474
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 256
	type: sts-test-256
	metrics:
	- type: pearson_cosine
	value: 0.8124139776213125
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8211087618006394
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7835377144525455
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7821679937822867
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.785247473429926
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7839505779526579
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5917356859640799
	name: Pearson Dot
	- type: spearman_dot
	value: 0.5785063907246168
	name: Spearman Dot
	- type: pearson_max
	value: 0.8124139776213125
	name: Pearson Max
	- type: spearman_max
	value: 0.8211087618006394
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 128
	type: sts-test-128
	metrics:
	- type: pearson_cosine
	value: 0.8079155052116238
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8190362316108264
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7794841536695422
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7786315620445202
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.781284034387115
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7812532216784576
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5714349767115854
	name: Pearson Dot
	- type: spearman_dot
	value: 0.5601824337480018
	name: Spearman Dot
	- type: pearson_max
	value: 0.8079155052116238
	name: Pearson Max
	- type: spearman_max
	value: 0.8190362316108264
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 64
	type: sts-test-64
	metrics:
	- type: pearson_cosine
	value: 0.7987987273687178
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8128864395227673
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7727564778562619
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7727917251788465
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7734618345058613
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7751195654319647
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5397052344713898
	name: Pearson Dot
	- type: spearman_dot
	value: 0.5279010425382445
	name: Spearman Dot
	- type: pearson_max
	value: 0.7987987273687178
	name: Pearson Max
	- type: spearman_max
	value: 0.8128864395227673
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 32
	type: sts-test-32
	metrics:
	- type: pearson_cosine
	value: 0.7720012222035324
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.7936423982593883
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7561303110063385
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7597271202292094
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7580804607973455
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7628041180101269
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.48898156184384284
	name: Pearson Dot
	- type: spearman_dot
	value: 0.47793665423562026
	name: Spearman Dot
	- type: pearson_max
	value: 0.7720012222035324
	name: Pearson Max
	- type: spearman_max
	value: 0.7936423982593883
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test 16
	type: sts-test-16
	metrics:
	- type: pearson_cosine
	value: 0.7137967594997888
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.7485767932719462
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7254358927069169
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.7339448581065434
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7274341928076351
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7382083636772965
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.385573703763858
	name: Pearson Dot
	- type: spearman_dot
	value: 0.3749226996833225
	name: Spearman Dot
	- type: pearson_max
	value: 0.7274341928076351
	name: Pearson Max
	- type: spearman_max
	value: 0.7485767932719462
	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 256-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: 256 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})
	(reduced_dim): Dense({'in_features': 768, 'out_features': 256, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
	)
	```

	## 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-reduced")
	# Run inference
	sentences = [
	'A boy is vacuuming.',
	'A little boy is vacuuming the floor.',
	'A woman is applying eye shadow.',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 256]

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

	\| Metric \| Value \|
	\|:--------------------\|:----------\|
	\| pearson_cosine \| 0.833 \|
	\| spearman_cosine \| 0.845 \|
	\| pearson_manhattan \| 0.8284 \|
	\| spearman_manhattan \| 0.8314 \|
	\| pearson_euclidean \| 0.8291 \|
	\| spearman_euclidean \| 0.8319 \|
	\| pearson_dot \| 0.7274 \|
	\| spearman_dot \| 0.7358 \|
	\| pearson_max \| 0.833 \|
	\| spearman_max \| 0.845 \|

	#### 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 \| 0.8266 \|
	\| spearman_cosine \| 0.8416 \|
	\| pearson_manhattan \| 0.825 \|
	\| spearman_manhattan \| 0.8277 \|
	\| pearson_euclidean \| 0.8256 \|
	\| spearman_euclidean \| 0.8285 \|
	\| pearson_dot \| 0.712 \|
	\| spearman_dot \| 0.7163 \|
	\| pearson_max \| 0.8266 \|
	\| spearman_max \| 0.8416 \|

	#### 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 \| 0.8171 \|
	\| spearman_cosine \| 0.8356 \|
	\| pearson_manhattan \| 0.8176 \|
	\| spearman_manhattan \| 0.8213 \|
	\| pearson_euclidean \| 0.8175 \|
	\| spearman_euclidean \| 0.8216 \|
	\| pearson_dot \| 0.6852 \|
	\| spearman_dot \| 0.6861 \|
	\| pearson_max \| 0.8176 \|
	\| spearman_max \| 0.8356 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-32`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.7964 \|
	\| spearman_cosine \| 0.8244 \|
	\| pearson_manhattan \| 0.7983 \|
	\| spearman_manhattan \| 0.8049 \|
	\| pearson_euclidean \| 0.8003 \|
	\| spearman_euclidean \| 0.807 \|
	\| pearson_dot \| 0.6312 \|
	\| spearman_dot \| 0.6277 \|
	\| pearson_max \| 0.8003 \|
	\| spearman_max \| 0.8244 \|

	#### Semantic Similarity
	* Dataset: `sts-dev-16`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.7401 \|
	\| spearman_cosine \| 0.7872 \|
	\| pearson_manhattan \| 0.761 \|
	\| spearman_manhattan \| 0.7761 \|
	\| pearson_euclidean \| 0.7645 \|
	\| spearman_euclidean \| 0.7794 \|
	\| pearson_dot \| 0.5202 \|
	\| spearman_dot \| 0.5115 \|
	\| pearson_max \| 0.7645 \|
	\| spearman_max \| 0.7872 \|

	#### 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 \| 0.8124 \|
	\| spearman_cosine \| 0.8211 \|
	\| pearson_manhattan \| 0.7835 \|
	\| spearman_manhattan \| 0.7822 \|
	\| pearson_euclidean \| 0.7852 \|
	\| spearman_euclidean \| 0.784 \|
	\| pearson_dot \| 0.5917 \|
	\| spearman_dot \| 0.5785 \|
	\| pearson_max \| 0.8124 \|
	\| spearman_max \| 0.8211 \|

	#### 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 \| 0.8079 \|
	\| spearman_cosine \| 0.819 \|
	\| pearson_manhattan \| 0.7795 \|
	\| spearman_manhattan \| 0.7786 \|
	\| pearson_euclidean \| 0.7813 \|
	\| spearman_euclidean \| 0.7813 \|
	\| pearson_dot \| 0.5714 \|
	\| spearman_dot \| 0.5602 \|
	\| pearson_max \| 0.8079 \|
	\| spearman_max \| 0.819 \|

	#### 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 \| 0.7988 \|
	\| spearman_cosine \| 0.8129 \|
	\| pearson_manhattan \| 0.7728 \|
	\| spearman_manhattan \| 0.7728 \|
	\| pearson_euclidean \| 0.7735 \|
	\| spearman_euclidean \| 0.7751 \|
	\| pearson_dot \| 0.5397 \|
	\| spearman_dot \| 0.5279 \|
	\| pearson_max \| 0.7988 \|
	\| spearman_max \| 0.8129 \|

	#### Semantic Similarity
	* Dataset: `sts-test-32`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.772 \|
	\| spearman_cosine \| 0.7936 \|
	\| pearson_manhattan \| 0.7561 \|
	\| spearman_manhattan \| 0.7597 \|
	\| pearson_euclidean \| 0.7581 \|
	\| spearman_euclidean \| 0.7628 \|
	\| pearson_dot \| 0.489 \|
	\| spearman_dot \| 0.4779 \|
	\| pearson_max \| 0.772 \|
	\| spearman_max \| 0.7936 \|

	#### Semantic Similarity
	* Dataset: `sts-test-16`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.7138 \|
	\| spearman_cosine \| 0.7486 \|
	\| pearson_manhattan \| 0.7254 \|
	\| spearman_manhattan \| 0.7339 \|
	\| pearson_euclidean \| 0.7274 \|
	\| spearman_euclidean \| 0.7382 \|
	\| pearson_dot \| 0.3856 \|
	\| spearman_dot \| 0.3749 \|
	\| pearson_max \| 0.7274 \|
	\| spearman_max \| 0.7486 \|

	<!--
	## 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": [
	256,
	128,
	64,
	32,
	16
	],
	"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": [
	256,
	128,
	64,
	32,
	16
	],
	"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-16_spearman_cosine \| sts-dev-256_spearman_cosine \| sts-dev-32_spearman_cosine \| sts-dev-64_spearman_cosine \| sts-test-128_spearman_cosine \| sts-test-16_spearman_cosine \| sts-test-256_spearman_cosine \| sts-test-32_spearman_cosine \| sts-test-64_spearman_cosine \|
	\|:------:\|:----:\|:-------------:\|:-------:\|:---------------------------:\|:--------------------------:\|:---------------------------:\|:--------------------------:\|:--------------------------:\|:----------------------------:\|:---------------------------:\|:----------------------------:\|:---------------------------:\|:---------------------------:\|
	\| 0.0229 \| 100 \| 21.0363 \| 14.2448 \| 0.7856 \| 0.7417 \| 0.7873 \| 0.7751 \| 0.7846 \| - \| - \| - \| - \| - \|
	\| 0.0459 \| 200 \| 11.1093 \| 13.4736 \| 0.7877 \| 0.7298 \| 0.7861 \| 0.7687 \| 0.7798 \| - \| - \| - \| - \| - \|
	\| 0.0688 \| 300 \| 10.1847 \| 13.7191 \| 0.7877 \| 0.7284 \| 0.7898 \| 0.7617 \| 0.7755 \| - \| - \| - \| - \| - \|
	\| 0.0918 \| 400 \| 9.356 \| 13.2955 \| 0.7906 \| 0.7385 \| 0.7914 \| 0.7715 \| 0.7799 \| - \| - \| - \| - \| - \|
	\| 0.1147 \| 500 \| 8.9318 \| 12.8099 \| 0.7889 \| 0.7346 \| 0.7910 \| 0.7690 \| 0.7801 \| - \| - \| - \| - \| - \|
	\| 0.1376 \| 600 \| 8.5293 \| 13.7384 \| 0.7814 \| 0.7362 \| 0.7866 \| 0.7656 \| 0.7736 \| - \| - \| - \| - \| - \|
	\| 0.1606 \| 700 \| 8.7589 \| 13.4466 \| 0.7899 \| 0.7467 \| 0.7945 \| 0.7770 \| 0.7847 \| - \| - \| - \| - \| - \|
	\| 0.1835 \| 800 \| 7.7941 \| 13.6734 \| 0.7960 \| 0.7526 \| 0.7986 \| 0.7800 \| 0.7894 \| - \| - \| - \| - \| - \|
	\| 0.2065 \| 900 \| 7.9183 \| 12.9082 \| 0.7885 \| 0.7470 \| 0.7966 \| 0.7705 \| 0.7803 \| - \| - \| - \| - \| - \|
	\| 0.2294 \| 1000 \| 7.3669 \| 13.2827 \| 0.7751 \| 0.7181 \| 0.7822 \| 0.7557 \| 0.7675 \| - \| - \| - \| - \| - \|
	\| 0.2524 \| 1100 \| 7.6205 \| 13.0227 \| 0.7875 \| 0.7373 \| 0.7914 \| 0.7730 \| 0.7828 \| - \| - \| - \| - \| - \|
	\| 0.2753 \| 1200 \| 7.4308 \| 13.4980 \| 0.7844 \| 0.7373 \| 0.7890 \| 0.7709 \| 0.7755 \| - \| - \| - \| - \| - \|
	\| 0.2982 \| 1300 \| 7.3625 \| 12.8380 \| 0.7984 \| 0.7520 \| 0.8032 \| 0.7824 \| 0.7915 \| - \| - \| - \| - \| - \|
	\| 0.3212 \| 1400 \| 6.9421 \| 12.7016 \| 0.7912 \| 0.7358 \| 0.7960 \| 0.7749 \| 0.7850 \| - \| - \| - \| - \| - \|
	\| 0.3441 \| 1500 \| 7.0635 \| 13.2198 \| 0.8018 \| 0.7578 \| 0.8070 \| 0.7861 \| 0.7961 \| - \| - \| - \| - \| - \|
	\| 0.3671 \| 1600 \| 6.6682 \| 13.3225 \| 0.7906 \| 0.7522 \| 0.7944 \| 0.7763 \| 0.7849 \| - \| - \| - \| - \| - \|
	\| 0.3900 \| 1700 \| 6.42 \| 12.7381 \| 0.7984 \| 0.7449 \| 0.8021 \| 0.7806 \| 0.7911 \| - \| - \| - \| - \| - \|
	\| 0.4129 \| 1800 \| 6.659 \| 13.0247 \| 0.7947 \| 0.7461 \| 0.8002 \| 0.7808 \| 0.7876 \| - \| - \| - \| - \| - \|
	\| 0.4359 \| 1900 \| 6.1664 \| 12.6814 \| 0.7893 \| 0.7312 \| 0.7959 \| 0.7700 \| 0.7807 \| - \| - \| - \| - \| - \|
	\| 0.4588 \| 2000 \| 6.392 \| 13.0238 \| 0.7935 \| 0.7354 \| 0.7987 \| 0.7758 \| 0.7860 \| - \| - \| - \| - \| - \|
	\| 0.4818 \| 2100 \| 6.177 \| 12.8833 \| 0.7891 \| 0.7428 \| 0.7924 \| 0.7723 \| 0.7801 \| - \| - \| - \| - \| - \|
	\| 0.5047 \| 2200 \| 6.0411 \| 12.5269 \| 0.7836 \| 0.7400 \| 0.7875 \| 0.7664 \| 0.7765 \| - \| - \| - \| - \| - \|
	\| 0.5276 \| 2300 \| 6.1506 \| 13.4349 \| 0.7741 \| 0.7350 \| 0.7803 \| 0.7556 \| 0.7634 \| - \| - \| - \| - \| - \|
	\| 0.5506 \| 2400 \| 6.109 \| 12.6996 \| 0.7808 \| 0.7326 \| 0.7860 \| 0.7663 \| 0.7735 \| - \| - \| - \| - \| - \|
	\| 0.5735 \| 2500 \| 6.2849 \| 13.2831 \| 0.7874 \| 0.7365 \| 0.7932 \| 0.7727 \| 0.7794 \| - \| - \| - \| - \| - \|
	\| 0.5965 \| 2600 \| 6.0658 \| 12.9425 \| 0.7988 \| 0.7481 \| 0.8042 \| 0.7818 \| 0.7889 \| - \| - \| - \| - \| - \|
	\| 0.6194 \| 2700 \| 6.0646 \| 13.0144 \| 0.7965 \| 0.7509 \| 0.8010 \| 0.7800 \| 0.7875 \| - \| - \| - \| - \| - \|
	\| 0.6423 \| 2800 \| 6.0795 \| 12.7602 \| 0.7912 \| 0.7472 \| 0.7937 \| 0.7778 \| 0.7818 \| - \| - \| - \| - \| - \|
	\| 0.6653 \| 2900 \| 6.2407 \| 13.2381 \| 0.7829 \| 0.7381 \| 0.7873 \| 0.7664 \| 0.7765 \| - \| - \| - \| - \| - \|
	\| 0.6882 \| 3000 \| 6.1872 \| 12.9064 \| 0.7942 \| 0.7516 \| 0.7965 \| 0.7793 \| 0.7857 \| - \| - \| - \| - \| - \|
	\| 0.7112 \| 3100 \| 5.8987 \| 12.9323 \| 0.8065 \| 0.7585 \| 0.8087 \| 0.7909 \| 0.7989 \| - \| - \| - \| - \| - \|
	\| 0.7341 \| 3200 \| 5.996 \| 13.1017 \| 0.7971 \| 0.7566 \| 0.8005 \| 0.7811 \| 0.7889 \| - \| - \| - \| - \| - \|
	\| 0.7571 \| 3300 \| 5.3748 \| 12.7601 \| 0.8398 \| 0.7881 \| 0.8441 \| 0.8232 \| 0.8337 \| - \| - \| - \| - \| - \|
	\| 0.7800 \| 3400 \| 4.0798 \| 12.7221 \| 0.8400 \| 0.7908 \| 0.8440 \| 0.8255 \| 0.8342 \| - \| - \| - \| - \| - \|
	\| 0.8029 \| 3500 \| 3.6024 \| 12.5445 \| 0.8408 \| 0.7892 \| 0.8447 \| 0.8247 \| 0.8347 \| - \| - \| - \| - \| - \|
	\| 0.8259 \| 3600 \| 3.4619 \| 12.6025 \| 0.8405 \| 0.7883 \| 0.8442 \| 0.8255 \| 0.8347 \| - \| - \| - \| - \| - \|
	\| 0.8488 \| 3700 \| 3.2288 \| 12.6636 \| 0.8388 \| 0.7872 \| 0.8433 \| 0.8226 \| 0.8330 \| - \| - \| - \| - \| - \|
	\| 0.8718 \| 3800 \| 3.0543 \| 12.6475 \| 0.8386 \| 0.7834 \| 0.8427 \| 0.8229 \| 0.8330 \| - \| - \| - \| - \| - \|
	\| 0.8947 \| 3900 \| 3.0368 \| 12.5390 \| 0.8407 \| 0.7845 \| 0.8444 \| 0.8227 \| 0.8346 \| - \| - \| - \| - \| - \|
	\| 0.9176 \| 4000 \| 2.9591 \| 12.5709 \| 0.8419 \| 0.7864 \| 0.8456 \| 0.8245 \| 0.8359 \| - \| - \| - \| - \| - \|
	\| 0.9406 \| 4100 \| 2.944 \| 12.6029 \| 0.8415 \| 0.7868 \| 0.8452 \| 0.8245 \| 0.8359 \| - \| - \| - \| - \| - \|
	\| 0.9635 \| 4200 \| 2.9032 \| 12.5514 \| 0.8423 \| 0.7888 \| 0.8455 \| 0.8254 \| 0.8363 \| - \| - \| - \| - \| - \|
	\| 0.9865 \| 4300 \| 2.838 \| 12.6054 \| 0.8416 \| 0.7872 \| 0.8450 \| 0.8244 \| 0.8356 \| - \| - \| - \| - \| - \|
	\| 1.0 \| 4359 \| - \| - \| - \| - \| - \| - \| - \| 0.8190 \| 0.7486 \| 0.8211 \| 0.7936 \| 0.8129 \|


	### Environmental Impact
	Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
	- Energy Consumed: 0.244 kWh
	- Carbon Emitted: 0.095 kg of CO2
	- Hours Used: 0.923 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.
	-->