---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:43318
- loss:MultipleNegativesRankingLoss
base_model: intfloat/multilingual-e5-large
widget:
- source_sentence: 'query: 3PL 사용 시의 비용 절감 메커니즘은 어떤 것이 있나요?'
sentences:
- 'passage: 3 Dimension-Through Silicon Via (Technical)'
- 'passage: Third Party Logistics (상업)'
- 'passage: Authorization Account Answer (Technical)'
- source_sentence: 'query: How can ACE be utilized?'
sentences:
- 'passage: Audio Connecting Equipment (Applicational)'
- 'passage: Access Class-Barring (활용)'
- 'passage: Abort Accept (기술)'
- source_sentence: 'query: What makes the 1x RTT technology significant?'
sentences:
- 'passage: Ab Wire Test (Conceptual)'
- 'passage: CDMA2000 1x Radio Transmission Technology (Conceptual)'
- 'passage: Authentication, Authorization, Accounting (기술)'
- source_sentence: 'query: 2WPD의 전력 분배 방식은 어떻게 이루어지나요?'
sentences:
- 'passage: Triple Digital Encryption Standard (기술)'
- 'passage: Air Baffle (Conceptual)'
- 'passage: 2 Way Power Divider (기술)'
- source_sentence: 'query: 3D-TSV가 반도체 설계에 미치는 영향은 무엇인가요?'
sentences:
- 'passage: Available Bit Rate (Applicational)'
- 'passage: Average Bouncing Busy Hour (개념)'
- 'passage: 3 Dimension-Through Silicon Via (기술)'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
model-index:
- name: SentenceTransformer based on intfloat/multilingual-e5-large
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: e5 eval real
type: e5-eval-real
metrics:
- type: cosine_accuracy@1
value: 0.9683
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9981
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9997
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9999
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.9683
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3326999999999999
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19994000000000006
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09999000000000001
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.9683
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9981
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9997
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9999
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9873905751741222
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.9830366666666664
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.9830414285714285
name: Cosine Map@100
---
# SentenceTransformer based on intfloat/multilingual-e5-large
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on the train dataset. 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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- train
### 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': 256, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
(1): Pooling({'word_embedding_dimension': 1024, '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})
(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("sentence_transformers_model_id")
# Run inference
sentences = [
'query: 3D-TSV가 반도체 설계에 미치는 영향은 무엇인가요?',
'passage: 3 Dimension-Through Silicon Via (기술)',
'passage: Available Bit Rate (Applicational)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, 0.8098, -0.1741],
# [ 0.8098, 1.0000, -0.2449],
# [-0.1741, -0.2449, 1.0000]])
```
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `e5-eval-real`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.9683 |
| cosine_accuracy@3 | 0.9981 |
| cosine_accuracy@5 | 0.9997 |
| cosine_accuracy@10 | 0.9999 |
| cosine_precision@1 | 0.9683 |
| cosine_precision@3 | 0.3327 |
| cosine_precision@5 | 0.1999 |
| cosine_precision@10 | 0.1 |
| cosine_recall@1 | 0.9683 |
| cosine_recall@3 | 0.9981 |
| cosine_recall@5 | 0.9997 |
| cosine_recall@10 | 0.9999 |
| **cosine_ndcg@10** | **0.9874** |
| cosine_mrr@10 | 0.983 |
| cosine_map@100 | 0.983 |
## Training Details
### Training Dataset
#### train
* Dataset: train
* Size: 43,318 training samples
* Columns: 0 and 1
* Approximate statistics based on the first 1000 samples:
| | 0 | 1 |
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details |
query: ABPL은 ATM의 기초 속도를 지원하는 물리 계층 장치로 어떻게 구성되나요? | passage: ATM Base Rate Physical Layer Unit (기술) |
| query: How is the ABPL configured as a physical layer unit supporting the ATM base rate? | passage: ATM Base Rate Physical Layer Unit (Technical) |
| query: ABPL의 역할은 ATM 네트워크에서 무엇을 의미하나요? | passage: ATM Base Rate Physical Layer Unit (개념) |
* Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `learning_rate`: 1e-05
- `weight_decay`: 0.01
- `lr_scheduler_type`: cosine
- `warmup_ratio`: 0.1
- `bf16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters