---
base_model: BAAI/bge-m3
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:24000
- loss:TripletLoss
- loss:MultipleNegativesRankingLoss
- loss:CoSENTLoss
widget:
- source_sentence: installere gulv på lite loft
sentences:
- 'query: gjerdeoppsett'
- 'query: støping av helleplass med skiferheller, 100 kvm'
- 'query: legge nytt gulv på lite loft'
- source_sentence: Montering av Baderomsinnredning
sentences:
- Installere baderomsmøbler
- Montere dusjkabinett
- lage fasadetegninger
- source_sentence: '* Fortsatt ledig: Klippe gress'
sentences:
- Klippe gress i hagen
- Male hus utvendig
- Rydde hage
- source_sentence: Totalrenovering av bad ca 6m2
sentences:
- Installere dusjkabinett
- Pusse opp bad
- Skifte tak
- source_sentence: Skorstein/pipe har fått avvik ved inspeksjon av feier
sentences:
- Bygge garasje med skråtak
- Graving og planering av tomt
- Feier har funnet feil på skorstein
model-index:
- name: SentenceTransformer based on BAAI/bge-m3
results:
- task:
type: triplet
name: Triplet
dataset:
name: test triplet evaluation
type: test-triplet-evaluation
metrics:
- type: cosine_accuracy
value: 0.9704016913319239
name: Cosine Accuracy
- type: dot_accuracy
value: 0.02959830866807611
name: Dot Accuracy
- type: manhattan_accuracy
value: 0.9718111346018323
name: Manhattan Accuracy
- type: euclidean_accuracy
value: 0.9704016913319239
name: Euclidean Accuracy
- type: max_accuracy
value: 0.9718111346018323
name: Max Accuracy
---
# SentenceTransformer based on BAAI/bge-m3
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co./BAAI/bge-m3). It maps sentences & paragraphs to a 1024-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:** [BAAI/bge-m3](https://huggingface.co./BAAI/bge-m3)
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 1024 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 1024, '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})
(2): Normalize()
)
```
## 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/test11")
# Run inference
sentences = [
'Skorstein/pipe har fått avvik ved inspeksjon av feier',
'Feier har funnet feil på skorstein',
'Bygge garasje med skråtak',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# 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 | 0.9704 |
| dot_accuracy | 0.0296 |
| manhattan_accuracy | 0.9718 |
| euclidean_accuracy | 0.9704 |
| **max_accuracy** | **0.9718** |
## Training Details
### Training Datasets
#### Unnamed Dataset
* Size: 8,000 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 |
Rehabilitering av sokkeleleilighet 35 kvadrat
| Pusse opp sokkeleilighet
| Bygge ny sokkeleilighet
|
| Klippe hekk
| Beskjære hekk
| Felle trær
|
| Sette opp hybel kjøkken (KVIK)
| Montere hybelkjøkken
| Installere kjøkkeninnredning
|
* 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: 8,000 training samples
* Columns: sentence_0
and sentence_1
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 |
|:--------|:--------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | Ønsker pris på ny Mitsubishi Kirigamine 6,6 + montering + demontering
| query: prisforespørsel på Mitsubishi Kirigamine 6,6 med montering og demontering
|
| utskifting av store vinduer i enebolig
| query: vindusbytte i enebolig
|
| bygging
| query: konstruksjonsarbeid
|
* 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: 8,000 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 | Fliselegging av bad 6m2
| Legge fliser på kjøkken
| 0.55
|
| Fortsatt ledig: Tilbygg/påbygg
| Renovering og påbygg
| 0.65
|
| Gravejobb i gårdsplass (grus og leire)
| Gravejobb i hagen
| 0.65
|
* 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`: 1
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters