Hugging Face's logo

mrm8488
/
distilbert-base-matryoshka-sts-v2

Sentence Similarity
sentence-transformers
Safetensors
English
distilbert
feature-extraction
dataset_size:1K<n<10K
loss:MatryoshkaLoss
loss:CoSENTLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
distilbert-base-matryoshka-sts-v2 / README.md
mrm8488's picture
mrm8488
Add new SentenceTransformer model.
76de2ac verified
preview code
|
raw
history blame contribute delete
41.3 kB
---
language:
- en
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dataset_size:1K<n<10K
- loss:MatryoshkaLoss
- loss:CoSENTLoss
base_model: distilbert/distilbert-base-uncased
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 plane in the sky.
sentences:
- Two airplanes in the sky.
- Two women are sitting in a cafe.
- Turkey's PM Warns Against Protests
- source_sentence: A man jumping rope
sentences:
- A man climbs a rope.
- Blast on Indian train kills one
- Israel expands subsidies to settlements
- source_sentence: A baby is laughing.
sentences:
- The baby laughed in his car seat.
- The girl is playing the guitar.
- Bangladesh Islamist leader executed
- source_sentence: A plane is landing.
sentences:
- A animated airplane is landing.
- A man plays an acoustic guitar.
- Obama urges no new sanctions on Iran
- source_sentence: A boy is vacuuming.
sentences:
- A little boy is vacuuming the floor.
- Suicide bomber strikes in Syria
- 32 die in Bangladesh protest
pipeline_tag: sentence-similarity
model-index:
- name: SentenceTransformer based on distilbert/distilbert-base-uncased
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 768
type: sts-dev-768
metrics:
- type: pearson_cosine
value: 0.8580007118837358
name: Pearson Cosine
- type: spearman_cosine
value: 0.871820299536176
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8579597824452743
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8611676230134329
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8584693242993966
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8617539394714434
name: Spearman Euclidean
- type: pearson_dot
value: 0.6259192943899555
name: Pearson Dot
- type: spearman_dot
value: 0.6245849846631494
name: Spearman Dot
- type: pearson_max
value: 0.8584693242993966
name: Pearson Max
- type: spearman_max
value: 0.871820299536176
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 512
type: sts-dev-512
metrics:
- type: pearson_cosine
value: 0.855328467168775
name: Pearson Cosine
- type: spearman_cosine
value: 0.8708546925464771
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8571701704416792
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8609603329646862
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8577665956034857
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8611867637483455
name: Spearman Euclidean
- type: pearson_dot
value: 0.6301839390729895
name: Pearson Dot
- type: spearman_dot
value: 0.6312551259723912
name: Spearman Dot
- type: pearson_max
value: 0.8577665956034857
name: Pearson Max
- type: spearman_max
value: 0.8708546925464771
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 256
type: sts-dev-256
metrics:
- type: pearson_cosine
value: 0.8534192140857989
name: Pearson Cosine
- type: spearman_cosine
value: 0.8684742287834586
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8550376893582918
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8595873940460774
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.855243500036296
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8595389790366662
name: Spearman Euclidean
- type: pearson_dot
value: 0.5692600956239565
name: Pearson Dot
- type: spearman_dot
value: 0.5631798664802073
name: Spearman Dot
- type: pearson_max
value: 0.855243500036296
name: Pearson Max
- type: spearman_max
value: 0.8684742287834586
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 128
type: sts-dev-128
metrics:
- type: pearson_cosine
value: 0.8437376978373121
name: Pearson Cosine
- type: spearman_cosine
value: 0.8634082420330794
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8454596574177755
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.85188111210432
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8479887421152008
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8537259447832961
name: Spearman Euclidean
- type: pearson_dot
value: 0.5513203019384504
name: Pearson Dot
- type: spearman_dot
value: 0.5500687993669725
name: Spearman Dot
- type: pearson_max
value: 0.8479887421152008
name: Pearson Max
- type: spearman_max
value: 0.8634082420330794
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 64
type: sts-dev-64
metrics:
- type: pearson_cosine
value: 0.8272184719216283
name: Pearson Cosine
- type: spearman_cosine
value: 0.8541030591238341
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8307462071466211
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8406982840852595
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8342382781891662
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8427338906559259
name: Spearman Euclidean
- type: pearson_dot
value: 0.494520518114596
name: Pearson Dot
- type: spearman_dot
value: 0.49218360841938574
name: Spearman Dot
- type: pearson_max
value: 0.8342382781891662
name: Pearson Max
- type: spearman_max
value: 0.8541030591238341
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 32
type: sts-dev-32
metrics:
- type: pearson_cosine
value: 0.795037446434113
name: Pearson Cosine
- type: spearman_cosine
value: 0.8337679875014413
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8120635303724889
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8249212312847407
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8157607542813738
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8262833782950811
name: Spearman Euclidean
- type: pearson_dot
value: 0.44442829473227297
name: Pearson Dot
- type: spearman_dot
value: 0.4333209339301445
name: Spearman Dot
- type: pearson_max
value: 0.8157607542813738
name: Pearson Max
- type: spearman_max
value: 0.8337679875014413
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev 16
type: sts-dev-16
metrics:
- type: pearson_cosine
value: 0.7402920507586056
name: Pearson Cosine
- type: spearman_cosine
value: 0.7953398971914366
name: Spearman Cosine
- type: pearson_manhattan
value: 0.7661819958789702
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.7806209887724272
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.7753319460863385
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.788448392758016
name: Spearman Euclidean
- type: pearson_dot
value: 0.2914268467178465
name: Pearson Dot
- type: spearman_dot
value: 0.2731801701260987
name: Spearman Dot
- type: pearson_max
value: 0.7753319460863385
name: Pearson Max
- type: spearman_max
value: 0.7953398971914366
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 768
type: sts-test-768
metrics:
- type: pearson_cosine
value: 0.8355126555886146
name: Pearson Cosine
- type: spearman_cosine
value: 0.8474343771835785
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8477769261693708
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8440487632905719
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8482353907773731
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8443357402859023
name: Spearman Euclidean
- type: pearson_dot
value: 0.575155372226532
name: Pearson Dot
- type: spearman_dot
value: 0.5645826036063977
name: Spearman Dot
- type: pearson_max
value: 0.8482353907773731
name: Pearson Max
- type: spearman_max
value: 0.8474343771835785
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 512
type: sts-test-512
metrics:
- type: pearson_cosine
value: 0.8345636179092932
name: Pearson Cosine
- type: spearman_cosine
value: 0.847969741682177
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8471375569231226
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8432315278152519
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8475673449165414
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8438566473590643
name: Spearman Euclidean
- type: pearson_dot
value: 0.5890647647307824
name: Pearson Dot
- type: spearman_dot
value: 0.579599198660516
name: Spearman Dot
- type: pearson_max
value: 0.8475673449165414
name: Pearson Max
- type: spearman_max
value: 0.847969741682177
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 256
type: sts-test-256
metrics:
- type: pearson_cosine
value: 0.8264268046184008
name: Pearson Cosine
- type: spearman_cosine
value: 0.8414784020776254
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8414377075419083
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8388634084489552
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8423455168447094
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8400797815114284
name: Spearman Euclidean
- type: pearson_dot
value: 0.5229860109488433
name: Pearson Dot
- type: spearman_dot
value: 0.5099269577284724
name: Spearman Dot
- type: pearson_max
value: 0.8423455168447094
name: Pearson Max
- type: spearman_max
value: 0.8414784020776254
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 128
type: sts-test-128
metrics:
- type: pearson_cosine
value: 0.8189773000477083
name: Pearson Cosine
- type: spearman_cosine
value: 0.837625236881656
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8349887918183595
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8336489133404312
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8365085956274743
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8347627903646608
name: Spearman Euclidean
- type: pearson_dot
value: 0.49799738412782535
name: Pearson Dot
- type: spearman_dot
value: 0.48970409354637134
name: Spearman Dot
- type: pearson_max
value: 0.8365085956274743
name: Pearson Max
- type: spearman_max
value: 0.837625236881656
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 64
type: sts-test-64
metrics:
- type: pearson_cosine
value: 0.8062259318483077
name: Pearson Cosine
- type: spearman_cosine
value: 0.8292433269349447
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8236527010227455
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8243846152203906
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8273451113428331
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8269777736926925
name: Spearman Euclidean
- type: pearson_dot
value: 0.4318247709105578
name: Pearson Dot
- type: spearman_dot
value: 0.4325030690630689
name: Spearman Dot
- type: pearson_max
value: 0.8273451113428331
name: Pearson Max
- type: spearman_max
value: 0.8292433269349447
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 32
type: sts-test-32
metrics:
- type: pearson_cosine
value: 0.7769698706658718
name: Pearson Cosine
- type: spearman_cosine
value: 0.813231133965274
name: Spearman Cosine
- type: pearson_manhattan
value: 0.8040659399939705
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.8083901845044422
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.8089540323890078
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.8126434700070444
name: Spearman Euclidean
- type: pearson_dot
value: 0.3721968691924307
name: Pearson Dot
- type: spearman_dot
value: 0.36359211044547146
name: Spearman Dot
- type: pearson_max
value: 0.8089540323890078
name: Pearson Max
- type: spearman_max
value: 0.813231133965274
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 16
type: sts-test-16
metrics:
- type: pearson_cosine
value: 0.7350580362911046
name: Pearson Cosine
- type: spearman_cosine
value: 0.7811480253828886
name: Spearman Cosine
- type: pearson_manhattan
value: 0.7686995805327835
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.7767016091591996
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.7732639293607727
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.7798783495241994
name: Spearman Euclidean
- type: pearson_dot
value: 0.25479413300114095
name: Pearson Dot
- type: spearman_dot
value: 0.24117846955339683
name: Spearman Dot
- type: pearson_max
value: 0.7732639293607727
name: Pearson Max
- type: spearman_max
value: 0.7811480253828886
name: Spearman Max
---
# SentenceTransformer based on distilbert/distilbert-base-uncased
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) 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/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
- **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: DistilBertModel
(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("mrm8488/distilbert-base-matryoshka-sts-v2")
# Run inference
sentences = [
'A boy is vacuuming.',
'A little boy is vacuuming the floor.',
'Suicide bomber strikes in Syria',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# 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
#### Semantic Similarity
* Dataset: `sts-dev-768`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.858 |
| **spearman_cosine** | **0.8718** |
| pearson_manhattan | 0.858 |
| spearman_manhattan | 0.8612 |
| pearson_euclidean | 0.8585 |
| spearman_euclidean | 0.8618 |
| pearson_dot | 0.6259 |
| spearman_dot | 0.6246 |
| pearson_max | 0.8585 |
| spearman_max | 0.8718 |
#### Semantic Similarity
* Dataset: `sts-dev-512`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8553 |
| **spearman_cosine** | **0.8709** |
| pearson_manhattan | 0.8572 |
| spearman_manhattan | 0.861 |
| pearson_euclidean | 0.8578 |
| spearman_euclidean | 0.8612 |
| pearson_dot | 0.6302 |
| spearman_dot | 0.6313 |
| pearson_max | 0.8578 |
| spearman_max | 0.8709 |
#### Semantic Similarity
* Dataset: `sts-dev-256`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8534 |
| **spearman_cosine** | **0.8685** |
| pearson_manhattan | 0.855 |
| spearman_manhattan | 0.8596 |
| pearson_euclidean | 0.8552 |
| spearman_euclidean | 0.8595 |
| pearson_dot | 0.5693 |
| spearman_dot | 0.5632 |
| pearson_max | 0.8552 |
| spearman_max | 0.8685 |
#### Semantic Similarity
* Dataset: `sts-dev-128`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8437 |
| **spearman_cosine** | **0.8634** |
| pearson_manhattan | 0.8455 |
| spearman_manhattan | 0.8519 |
| pearson_euclidean | 0.848 |
| spearman_euclidean | 0.8537 |
| pearson_dot | 0.5513 |
| spearman_dot | 0.5501 |
| pearson_max | 0.848 |
| spearman_max | 0.8634 |
#### Semantic Similarity
* Dataset: `sts-dev-64`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8272 |
| **spearman_cosine** | **0.8541** |
| pearson_manhattan | 0.8307 |
| spearman_manhattan | 0.8407 |
| pearson_euclidean | 0.8342 |
| spearman_euclidean | 0.8427 |
| pearson_dot | 0.4945 |
| spearman_dot | 0.4922 |
| pearson_max | 0.8342 |
| spearman_max | 0.8541 |
#### Semantic Similarity
* Dataset: `sts-dev-32`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.795 |
| **spearman_cosine** | **0.8338** |
| pearson_manhattan | 0.8121 |
| spearman_manhattan | 0.8249 |
| pearson_euclidean | 0.8158 |
| spearman_euclidean | 0.8263 |
| pearson_dot | 0.4444 |
| spearman_dot | 0.4333 |
| pearson_max | 0.8158 |
| spearman_max | 0.8338 |
#### Semantic Similarity
* Dataset: `sts-dev-16`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.7403 |
| **spearman_cosine** | **0.7953** |
| pearson_manhattan | 0.7662 |
| spearman_manhattan | 0.7806 |
| pearson_euclidean | 0.7753 |
| spearman_euclidean | 0.7884 |
| pearson_dot | 0.2914 |
| spearman_dot | 0.2732 |
| pearson_max | 0.7753 |
| spearman_max | 0.7953 |
#### Semantic Similarity
* Dataset: `sts-test-768`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8355 |
| **spearman_cosine** | **0.8474** |
| pearson_manhattan | 0.8478 |
| spearman_manhattan | 0.844 |
| pearson_euclidean | 0.8482 |
| spearman_euclidean | 0.8443 |
| pearson_dot | 0.5752 |
| spearman_dot | 0.5646 |
| pearson_max | 0.8482 |
| spearman_max | 0.8474 |
#### Semantic Similarity
* Dataset: `sts-test-512`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:----------|
| pearson_cosine | 0.8346 |
| **spearman_cosine** | **0.848** |
| pearson_manhattan | 0.8471 |
| spearman_manhattan | 0.8432 |
| pearson_euclidean | 0.8476 |
| spearman_euclidean | 0.8439 |
| pearson_dot | 0.5891 |
| spearman_dot | 0.5796 |
| pearson_max | 0.8476 |
| spearman_max | 0.848 |
#### Semantic Similarity
* Dataset: `sts-test-256`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8264 |
| **spearman_cosine** | **0.8415** |
| pearson_manhattan | 0.8414 |
| spearman_manhattan | 0.8389 |
| pearson_euclidean | 0.8423 |
| spearman_euclidean | 0.8401 |
| pearson_dot | 0.523 |
| spearman_dot | 0.5099 |
| pearson_max | 0.8423 |
| spearman_max | 0.8415 |
#### Semantic Similarity
* Dataset: `sts-test-128`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.819 |
| **spearman_cosine** | **0.8376** |
| pearson_manhattan | 0.835 |
| spearman_manhattan | 0.8336 |
| pearson_euclidean | 0.8365 |
| spearman_euclidean | 0.8348 |
| pearson_dot | 0.498 |
| spearman_dot | 0.4897 |
| pearson_max | 0.8365 |
| spearman_max | 0.8376 |
#### Semantic Similarity
* Dataset: `sts-test-64`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.8062 |
| **spearman_cosine** | **0.8292** |
| pearson_manhattan | 0.8237 |
| spearman_manhattan | 0.8244 |
| pearson_euclidean | 0.8273 |
| spearman_euclidean | 0.827 |
| pearson_dot | 0.4318 |
| spearman_dot | 0.4325 |
| pearson_max | 0.8273 |
| spearman_max | 0.8292 |
#### Semantic Similarity
* Dataset: `sts-test-32`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.777 |
| **spearman_cosine** | **0.8132** |
| pearson_manhattan | 0.8041 |
| spearman_manhattan | 0.8084 |
| pearson_euclidean | 0.809 |
| spearman_euclidean | 0.8126 |
| pearson_dot | 0.3722 |
| spearman_dot | 0.3636 |
| pearson_max | 0.809 |
| spearman_max | 0.8132 |
#### Semantic Similarity
* Dataset: `sts-test-16`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.7351 |
| **spearman_cosine** | **0.7811** |
| pearson_manhattan | 0.7687 |
| spearman_manhattan | 0.7767 |
| pearson_euclidean | 0.7733 |
| spearman_euclidean | 0.7799 |
| pearson_dot | 0.2548 |
| spearman_dot | 0.2412 |
| pearson_max | 0.7733 |
| spearman_max | 0.7811 |
<!--
## 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/stsb
* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
* Size: 5,749 training 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: 6 tokens</li><li>mean: 10.0 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.95 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
* Samples:
| sentence1 | sentence2 | score |
|:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
| <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
| <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> |
| <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "CoSENTLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64,
32,
16
],
"matryoshka_weights": [
1,
1,
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: 15.1 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 53 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/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
```json
{
"loss": "CoSENTLoss",
"matryoshka_dims": [
768,
512,
256,
128,
64,
32,
16
],
"matryoshka_weights": [
1,
1,
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`: 4
- `warmup_ratio`: 0.1
- `bf16`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 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`: 4
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `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`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `batch_sampler`: batch_sampler
- `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-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine | sts-test-128_spearman_cosine | sts-test-16_spearman_cosine | sts-test-256_spearman_cosine | sts-test-32_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
|:------:|:----:|:-------------:|:-------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
| 2.2222 | 100 | 60.4066 | 60.8718 | 0.8634 | 0.7953 | 0.8685 | 0.8338 | 0.8709 | 0.8541 | 0.8718 | - | - | - | - | - | - | - |
| 4.0 | 180 | - | - | - | - | - | - | - | - | - | 0.8376 | 0.7811 | 0.8415 | 0.8132 | 0.8480 | 0.8292 | 0.8474 |
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.0
- Transformers: 4.41.1
- PyTorch: 2.3.0+cu121
- Accelerate: 0.30.1
- 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",
}
```
#### 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}
}
```
#### CoSENTLoss
```bibtex
@online{kexuefm-8847,
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
author={Su Jianlin},
year={2022},
month={Jan},
url={https://kexue.fm/archives/8847},
}
```
<!--
## 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.*
-->