---
base_model: NbAiLab/nb-sbert-base
datasets: []
language: []
library_name: sentence-transformers
metrics:
- cosine_accuracy
- dot_accuracy
- manhattan_accuracy
- euclidean_accuracy
- max_accuracy
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:96724
- loss:TripletLoss
- loss:MultipleNegativesRankingLoss
- loss:CoSENTLoss
widget:
- source_sentence: Fjerne 60 cm snø fra enebolig på 100 kvadratmeter
sentences:
- 'query: montere solskjerming inne'
- 'query: 150 meter grøfting'
- 'query: Snømåking på enebolig, 100 kvadratmeter'
- source_sentence: Renovering av bad
sentences:
- Asfaltere innkjørsel
- Nye garasjeporter m/åpner
- Totalrenovering av lite bad i Lillestrøm
- source_sentence: Lite tilbygg til eksisterende bolig
sentences:
- Renovere bolig
- Vi skal pusse opp kjøkken
- Bygge tilbygg
- source_sentence: Gulvlegging 6 kvm gang
sentences:
- Installere gulvvarme
- Montering av 8 spotlights brannsikre (4stk. på kjøket) og (2 stk i gangen)
- Legge parkett i gang
- source_sentence: Fullføre utvendig forefallent arbeid
sentences:
- Bytte av vinduer i hus
- elektriker på bolig på 120kvm
- Renovere bad
model-index:
- name: SentenceTransformer based on NbAiLab/nb-sbert-base
results:
- task:
type: triplet
name: Triplet
dataset:
name: test triplet evaluation
type: test-triplet-evaluation
metrics:
- type: cosine_accuracy
value: 0.9859055673009162
name: Cosine Accuracy
- type: dot_accuracy
value: 0.016913319238900635
name: Dot Accuracy
- type: manhattan_accuracy
value: 0.9844961240310077
name: Manhattan Accuracy
- type: euclidean_accuracy
value: 0.9837914023960536
name: Euclidean Accuracy
- type: max_accuracy
value: 0.9859055673009162
name: Max Accuracy
---
# SentenceTransformer based on NbAiLab/nb-sbert-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [NbAiLab/nb-sbert-base](https://huggingface.co./NbAiLab/nb-sbert-base). 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:** [NbAiLab/nb-sbert-base](https://huggingface.co./NbAiLab/nb-sbert-base)
- **Maximum Sequence Length:** 75 tokens
- **Output Dimensionality:** 768 tokens
- **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': 75, 'do_lower_case': False}) with Transformer model: BertModel
(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("ostoveland/SBertBaseMittanbudver1")
# Run inference
sentences = [
'Fullføre utvendig forefallent arbeid',
'elektriker på bolig på 120kvm',
'Renovere bad',
]
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
* Dataset: `test-triplet-evaluation`
* Evaluated with [TripletEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:-------------------|:-----------|
| cosine_accuracy | 0.9859 |
| dot_accuracy | 0.0169 |
| manhattan_accuracy | 0.9845 |
| euclidean_accuracy | 0.9838 |
| **max_accuracy** | **0.9859** |
## Training Details
### Training Datasets
#### Unnamed Dataset
* Size: 55,426 training samples
* Columns: sentence_0
, sentence_1
, and sentence_2
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | sentence_2 |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details |
Bygge støttemur
| Støttemur
| Bytte lås på dörr
|
| Understell bord i stål
| Lage stålunderstell til bord
| Bygge trebord
|
| Reparasjon vannbåren varme
| Vannbåren varme til enebolig
| * Fortsatt ledig: ombygning av eksisterende kjeller
|
* Loss: [TripletLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
#### Unnamed Dataset
* Size: 22,563 training samples
* Columns: sentence_0
and sentence_1
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | utforing av gavlvegg
| query: utforing av vegg
|
| Montere kjøkken
| query: kjøkkenmontering
|
| Sette opp lettvegg med skyvedør, bygge bod i carport, forlenge tak på carport
| query: bygge bod i carport
|
* Loss: [MultipleNegativesRankingLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
#### Unnamed Dataset
* Size: 18,735 training samples
* Columns: sentence_0
, sentence_1
, and label
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | label |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------|
| type | string | string | float |
| details | Renovering av hus - plantegninger og fasade
| elektriker på bolig på 120kvm
| 0.15
|
| Blending av innvendig dør
| Tette igjen døråpning
| 0.75
|
| Fortsatt ledig: Kappe teglstein på pipeløp
| Murearbeid
| 0.45
|
* Loss: [CoSENTLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "pairwise_cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `num_train_epochs`: 6
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters