---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:4957
- loss:AttributeTripletLoss
base_model: Alibaba-NLP/gte-base-en-v1.5
widget:
- source_sentence: Marianne Williamson
sentences:
- Francesco Sedita
- HarperCollins
- author
- publisher
- source_sentence: Brilliance Audio on CD Unabridged; Unabridged edition (September
22, 2009)
sentences:
- Alan Bradley
- publisher
- author
- Bearport Publishing
- source_sentence: 01 June 2003
sentences:
- '9785551553090'
- Signet (September 4, 1990)
- publication_date
- isbn_13
- source_sentence: The Elusive Pimpernel (Dover Value Editions)
sentences:
- HarperCollins; Illustrated. edition (May 15, 1974)
- publication_date
- The Real Benjamin Franklin (Vol. 2 of the American classic series)
- title
- source_sentence: Diana Gabaldon
sentences:
- publisher
- author
- Wong Herbert Yee
- Bloomsbury Publishing PLC
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy
- silhouette_cosine
- silhouette_euclidean
model-index:
- name: SentenceTransformer based on Alibaba-NLP/gte-base-en-v1.5
results:
- task:
type: triplet
name: Triplet
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy
value: 0.9509981870651245
name: Cosine Accuracy
- type: cosine_accuracy
value: 0.9656862616539001
name: Cosine Accuracy
- task:
type: silhouette
name: Silhouette
dataset:
name: Unknown
type: unknown
metrics:
- type: silhouette_cosine
value: 0.5749762654304504
name: Silhouette Cosine
- type: silhouette_euclidean
value: 0.49482977390289307
name: Silhouette Euclidean
- type: silhouette_cosine
value: 0.5844279527664185
name: Silhouette Cosine
- type: silhouette_euclidean
value: 0.5075943470001221
name: Silhouette Euclidean
---
# SentenceTransformer based on Alibaba-NLP/gte-base-en-v1.5
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5). 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:** [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5)
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
### 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': 8192, 'do_lower_case': False}) with Transformer model: NewModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("albertus-sussex/veriscrape-sbert-book-reference_2_to_verify_8-fold-5")
# Run inference
sentences = [
'Diana Gabaldon',
'Wong Herbert Yee',
'Bloomsbury Publishing PLC',
]
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]
```
## Evaluation
### Metrics
#### Triplet
* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:----------|
| **cosine_accuracy** | **0.951** |
#### Silhouette
* Evaluated with veriscrape.training.SilhouetteEvaluator
| Metric | Value |
|:----------------------|:----------|
| **silhouette_cosine** | **0.575** |
| silhouette_euclidean | 0.4948 |
#### Triplet
* Evaluated with [TripletEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| **cosine_accuracy** | **0.9657** |
#### Silhouette
* Evaluated with veriscrape.training.SilhouetteEvaluator
| Metric | Value |
|:----------------------|:-----------|
| **silhouette_cosine** | **0.5844** |
| silhouette_euclidean | 0.5076 |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 4,957 training samples
* Columns: anchor, positive, negative, pos_attr_name, and neg_attr_name
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative | pos_attr_name | neg_attr_name |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
| type | string | string | string | string | string |
| details |
Emotions Revealed: Recognizing Faces and Feelings to Improve Communication and Emotional Life | Zen and the Art of Motorcycle Maintenance: An Inquiry Into Values | HarperCollins Publishers Inc | title | publisher |
| Dell (2006) | Skyhorse Publishing (March 8, 2010) | Nemesis | publication_date | title |
| A Woman's Worth | Bone: v.1 | Dell (2006) | title | publication_date |
* Loss: veriscrape.training.AttributeTripletLoss with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Evaluation Dataset
#### Unnamed Dataset
* Size: 551 evaluation samples
* Columns: anchor, positive, negative, pos_attr_name, and neg_attr_name
* Approximate statistics based on the first 551 samples:
| | anchor | positive | negative | pos_attr_name | neg_attr_name |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
| type | string | string | string | string | string |
| details | As the Future Catches You: How Genomics & Other Forces Are Changing Your Life, Work, Health & Wealth | A Lesson Before Dying (Oprah's Book Club) | 978-1402220128 | title | isbn_13 |
| Vintage (July 8, 2003) | HarperCollins Publishers Inc | Vintage (September 8, 2009) | publisher | publication_date |
| 9780525423645 | 978-0978785109 | Dean Koontz | isbn_13 | author |
* Loss: veriscrape.training.AttributeTripletLoss with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `num_train_epochs`: 5
- `warmup_ratio`: 0.1
#### All Hyperparameters