---
base_model: colorfulscoop/sbert-base-ja
library_name: sentence-transformers
metrics:
- cosine_accuracy
- cosine_accuracy_threshold
- cosine_f1
- cosine_f1_threshold
- cosine_precision
- cosine_recall
- cosine_ap
- dot_accuracy
- dot_accuracy_threshold
- dot_f1
- dot_f1_threshold
- dot_precision
- dot_recall
- dot_ap
- manhattan_accuracy
- manhattan_accuracy_threshold
- manhattan_f1
- manhattan_f1_threshold
- manhattan_precision
- manhattan_recall
- manhattan_ap
- euclidean_accuracy
- euclidean_accuracy_threshold
- euclidean_f1
- euclidean_f1_threshold
- euclidean_precision
- euclidean_recall
- euclidean_ap
- max_accuracy
- max_accuracy_threshold
- max_f1
- max_f1_threshold
- max_precision
- max_recall
- max_ap
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:281
- loss:CoSENTLoss
widget:
- source_sentence: オッケー
sentences:
- どっち?
- 青いオーブがどこにあるか知ってる?
- ハーイ
- source_sentence: 昨日作ったのはビーフシチュー?
sentences:
- 魔法の残り香
- 家の外へ行こう
- 赤い染みが皿にあった
- source_sentence: 外を見てみよう
sentences:
- 物の見た目を変えられる魔法を使える人を知っている?
- これって?
- いつ手に入れたやつ?
- source_sentence: やっぱり、キャンドルがいい
sentences:
- 物体を変える
- きらい
- タイマツがいいな
- source_sentence: 棚からトマトがなくなってたから
sentences:
- こんにちは
- お鍋から辛い匂いがしたから
- スカーフは布袋の中?
model-index:
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: custom arc semantics data jp
type: custom-arc-semantics-data-jp
metrics:
- type: cosine_accuracy
value: 0.9824561403508771
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.9462370276451111
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0
name: Cosine F1
- type: cosine_f1_threshold
value: 0
name: Cosine F1 Threshold
- type: cosine_precision
value: 0
name: Cosine Precision
- type: cosine_recall
value: 0
name: Cosine Recall
- type: cosine_ap
value: -0.0
name: Cosine Ap
- type: dot_accuracy
value: 0.9824561403508771
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 546.0494384765625
name: Dot Accuracy Threshold
- type: dot_f1
value: 0
name: Dot F1
- type: dot_f1_threshold
value: 0
name: Dot F1 Threshold
- type: dot_precision
value: 0
name: Dot Precision
- type: dot_recall
value: 0
name: Dot Recall
- type: dot_ap
value: -0.0
name: Dot Ap
- type: manhattan_accuracy
value: 0.9824561403508771
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 119.43295288085938
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0
name: Manhattan F1
- type: manhattan_f1_threshold
value: 0
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0
name: Manhattan Precision
- type: manhattan_recall
value: 0
name: Manhattan Recall
- type: manhattan_ap
value: -0.0
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.9824561403508771
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 5.491857528686523
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0
name: Euclidean F1
- type: euclidean_f1_threshold
value: 0
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0
name: Euclidean Precision
- type: euclidean_recall
value: 0
name: Euclidean Recall
- type: euclidean_ap
value: -0.0
name: Euclidean Ap
- type: max_accuracy
value: 0.9824561403508771
name: Max Accuracy
- type: max_accuracy_threshold
value: 546.0494384765625
name: Max Accuracy Threshold
- type: max_f1
value: 0
name: Max F1
- type: max_f1_threshold
value: 0
name: Max F1 Threshold
- type: max_precision
value: 0
name: Max Precision
- type: max_recall
value: 0
name: Max Recall
- type: max_ap
value: -0.0
name: Max Ap
---
# SentenceTransformer based on colorfulscoop/sbert-base-ja
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv 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:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- csv
### 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: 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("sentence_transformers_model_id")
# Run inference
sentences = [
'棚からトマトがなくなってたから',
'お鍋から辛い匂いがしたから',
'スカーフは布袋の中?',
]
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
#### Binary Classification
* Dataset: `custom-arc-semantics-data-jp`
* Evaluated with [BinaryClassificationEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:---------|
| cosine_accuracy | 0.9825 |
| cosine_accuracy_threshold | 0.9462 |
| cosine_f1 | 0 |
| cosine_f1_threshold | 0 |
| cosine_precision | 0 |
| cosine_recall | 0 |
| cosine_ap | -0.0 |
| dot_accuracy | 0.9825 |
| dot_accuracy_threshold | 546.0494 |
| dot_f1 | 0 |
| dot_f1_threshold | 0 |
| dot_precision | 0 |
| dot_recall | 0 |
| dot_ap | -0.0 |
| manhattan_accuracy | 0.9825 |
| manhattan_accuracy_threshold | 119.433 |
| manhattan_f1 | 0 |
| manhattan_f1_threshold | 0 |
| manhattan_precision | 0 |
| manhattan_recall | 0 |
| manhattan_ap | -0.0 |
| euclidean_accuracy | 0.9825 |
| euclidean_accuracy_threshold | 5.4919 |
| euclidean_f1 | 0 |
| euclidean_f1_threshold | 0 |
| euclidean_precision | 0 |
| euclidean_recall | 0 |
| euclidean_ap | -0.0 |
| max_accuracy | 0.9825 |
| max_accuracy_threshold | 546.0494 |
| max_f1 | 0 |
| max_f1_threshold | 0 |
| max_precision | 0 |
| max_recall | 0 |
| **max_ap** | **-0.0** |
## Training Details
### Training Dataset
#### csv
* Dataset: csv
* Size: 281 training samples
* Columns: text1
, text2
, and label
* Approximate statistics based on the first 281 samples:
| | text1 | text2 | label |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
| type | string | string | int |
| details |
キャンドルがいいな
| タイマツ
| 0
|
| 物の形を変えられる人
| 物の形を変えられる人
| 0
|
| イベントについて教えて
| リリアンって誰?
| 0
|
* 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"
}
```
### Evaluation Dataset
#### csv
* Dataset: csv
* Size: 281 evaluation samples
* Columns: text1
, text2
, and label
* Approximate statistics based on the first 281 samples:
| | text1 | text2 | label |
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
| type | string | string | int |
| details | だれかが魔法で花をぬいぐるみに変えた
| これって?
| 0
|
| 他の選択肢をちょうだい
| どこを探したい?
| 0
|
| 昨日作ったのはビーフシチュー?
| 赤い染みが皿にあった
| 0
|
* 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
- `eval_strategy`: epoch
- `learning_rate`: 2e-05
- `num_train_epochs`: 5
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters