---
base_model: intfloat/multilingual-e5-small
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:2752
- loss:OnlineContrastiveLoss
widget:
- source_sentence: Would you want to be President?
sentences:
- Can you help me with my homework?
- How to bake cookies?
- Why do you want to be to president?
- source_sentence: Velocity of sound waves in the atmosphere
sentences:
- What is the speed of sound in air?
- What is the best/most memorable thing you've ever eaten and why?
- The `safe` option in the `to_spreadsheet` method controls whether a safe conversion
or not is needed for certain plant attributes to store the data in a SpreadsheetTable
or Row.
- source_sentence: Number of countries in the European Union
sentences:
- How many countries are in the European Union?
- Who painted the Sistine Chapel ceiling?
- The RecipeManager class is used to manage the downloading and extraction of recipes.
- source_sentence: Official currency of the USA
sentences:
- What is purpose of life?
- Files inside ZIP archives are accessed and yielded sequentially using iter_zip().
- What is the currency of the United States?
- source_sentence: Who wrote the book "1984"?
sentences:
- What is the speed of light?
- How to set up a home gym?
- Who wrote the book "To Kill a Mockingbird"?
model-index:
- name: SentenceTransformer based on intfloat/multilingual-e5-small
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: pair class dev
type: pair-class-dev
metrics:
- type: cosine_accuracy
value: 0.9456521739130435
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.8053532838821411
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9554896142433236
name: Cosine F1
- type: cosine_f1_threshold
value: 0.8053532838821411
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.92
name: Cosine Precision
- type: cosine_recall
value: 0.9938271604938271
name: Cosine Recall
- type: cosine_ap
value: 0.970102365862799
name: Cosine Ap
- type: dot_accuracy
value: 0.9456521739130435
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 0.8053532838821411
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.9554896142433236
name: Dot F1
- type: dot_f1_threshold
value: 0.8053532838821411
name: Dot F1 Threshold
- type: dot_precision
value: 0.92
name: Dot Precision
- type: dot_recall
value: 0.9938271604938271
name: Dot Recall
- type: dot_ap
value: 0.970102365862799
name: Dot Ap
- type: manhattan_accuracy
value: 0.9456521739130435
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 9.787351608276367
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.9554896142433236
name: Manhattan F1
- type: manhattan_f1_threshold
value: 9.787351608276367
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.92
name: Manhattan Precision
- type: manhattan_recall
value: 0.9938271604938271
name: Manhattan Recall
- type: manhattan_ap
value: 0.9698493258522533
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.9456521739130435
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 0.6239285469055176
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.9554896142433236
name: Euclidean F1
- type: euclidean_f1_threshold
value: 0.6239285469055176
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.92
name: Euclidean Precision
- type: euclidean_recall
value: 0.9938271604938271
name: Euclidean Recall
- type: euclidean_ap
value: 0.970102365862799
name: Euclidean Ap
- type: max_accuracy
value: 0.9456521739130435
name: Max Accuracy
- type: max_accuracy_threshold
value: 9.787351608276367
name: Max Accuracy Threshold
- type: max_f1
value: 0.9554896142433236
name: Max F1
- type: max_f1_threshold
value: 9.787351608276367
name: Max F1 Threshold
- type: max_precision
value: 0.92
name: Max Precision
- type: max_recall
value: 0.9938271604938271
name: Max Recall
- type: max_ap
value: 0.970102365862799
name: Max Ap
- task:
type: binary-classification
name: Binary Classification
dataset:
name: pair class test
type: pair-class-test
metrics:
- type: cosine_accuracy
value: 0.9456521739130435
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.8053532838821411
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9554896142433236
name: Cosine F1
- type: cosine_f1_threshold
value: 0.8053532838821411
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.92
name: Cosine Precision
- type: cosine_recall
value: 0.9938271604938271
name: Cosine Recall
- type: cosine_ap
value: 0.970102365862799
name: Cosine Ap
- type: dot_accuracy
value: 0.9456521739130435
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 0.8053532838821411
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.9554896142433236
name: Dot F1
- type: dot_f1_threshold
value: 0.8053532838821411
name: Dot F1 Threshold
- type: dot_precision
value: 0.92
name: Dot Precision
- type: dot_recall
value: 0.9938271604938271
name: Dot Recall
- type: dot_ap
value: 0.970102365862799
name: Dot Ap
- type: manhattan_accuracy
value: 0.9456521739130435
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 9.787351608276367
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.9554896142433236
name: Manhattan F1
- type: manhattan_f1_threshold
value: 9.787351608276367
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.92
name: Manhattan Precision
- type: manhattan_recall
value: 0.9938271604938271
name: Manhattan Recall
- type: manhattan_ap
value: 0.9698493258522533
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.9456521739130435
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 0.6239285469055176
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.9554896142433236
name: Euclidean F1
- type: euclidean_f1_threshold
value: 0.6239285469055176
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.92
name: Euclidean Precision
- type: euclidean_recall
value: 0.9938271604938271
name: Euclidean Recall
- type: euclidean_ap
value: 0.970102365862799
name: Euclidean Ap
- type: max_accuracy
value: 0.9456521739130435
name: Max Accuracy
- type: max_accuracy_threshold
value: 9.787351608276367
name: Max Accuracy Threshold
- type: max_f1
value: 0.9554896142433236
name: Max F1
- type: max_f1_threshold
value: 9.787351608276367
name: Max F1 Threshold
- type: max_precision
value: 0.92
name: Max Precision
- type: max_recall
value: 0.9938271604938271
name: Max Recall
- type: max_ap
value: 0.970102365862799
name: Max Ap
---
# SentenceTransformer based on intfloat/multilingual-e5-small
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). It maps sentences & paragraphs to a 384-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-small](https://huggingface.co/intfloat/multilingual-e5-small)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 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': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, '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("srikarvar/fine_tuned_model_17")
# Run inference
sentences = [
'Who wrote the book "1984"?',
'Who wrote the book "To Kill a Mockingbird"?',
'What is the speed of light?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
## Evaluation
### Metrics
#### Binary Classification
* Dataset: `pair-class-dev`
* Evaluated with [BinaryClassificationEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.9457 |
| cosine_accuracy_threshold | 0.8054 |
| cosine_f1 | 0.9555 |
| cosine_f1_threshold | 0.8054 |
| cosine_precision | 0.92 |
| cosine_recall | 0.9938 |
| cosine_ap | 0.9701 |
| dot_accuracy | 0.9457 |
| dot_accuracy_threshold | 0.8054 |
| dot_f1 | 0.9555 |
| dot_f1_threshold | 0.8054 |
| dot_precision | 0.92 |
| dot_recall | 0.9938 |
| dot_ap | 0.9701 |
| manhattan_accuracy | 0.9457 |
| manhattan_accuracy_threshold | 9.7874 |
| manhattan_f1 | 0.9555 |
| manhattan_f1_threshold | 9.7874 |
| manhattan_precision | 0.92 |
| manhattan_recall | 0.9938 |
| manhattan_ap | 0.9698 |
| euclidean_accuracy | 0.9457 |
| euclidean_accuracy_threshold | 0.6239 |
| euclidean_f1 | 0.9555 |
| euclidean_f1_threshold | 0.6239 |
| euclidean_precision | 0.92 |
| euclidean_recall | 0.9938 |
| euclidean_ap | 0.9701 |
| max_accuracy | 0.9457 |
| max_accuracy_threshold | 9.7874 |
| max_f1 | 0.9555 |
| max_f1_threshold | 9.7874 |
| max_precision | 0.92 |
| max_recall | 0.9938 |
| **max_ap** | **0.9701** |
#### Binary Classification
* Dataset: `pair-class-test`
* Evaluated with [BinaryClassificationEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.9457 |
| cosine_accuracy_threshold | 0.8054 |
| cosine_f1 | 0.9555 |
| cosine_f1_threshold | 0.8054 |
| cosine_precision | 0.92 |
| cosine_recall | 0.9938 |
| cosine_ap | 0.9701 |
| dot_accuracy | 0.9457 |
| dot_accuracy_threshold | 0.8054 |
| dot_f1 | 0.9555 |
| dot_f1_threshold | 0.8054 |
| dot_precision | 0.92 |
| dot_recall | 0.9938 |
| dot_ap | 0.9701 |
| manhattan_accuracy | 0.9457 |
| manhattan_accuracy_threshold | 9.7874 |
| manhattan_f1 | 0.9555 |
| manhattan_f1_threshold | 9.7874 |
| manhattan_precision | 0.92 |
| manhattan_recall | 0.9938 |
| manhattan_ap | 0.9698 |
| euclidean_accuracy | 0.9457 |
| euclidean_accuracy_threshold | 0.6239 |
| euclidean_f1 | 0.9555 |
| euclidean_f1_threshold | 0.6239 |
| euclidean_precision | 0.92 |
| euclidean_recall | 0.9938 |
| euclidean_ap | 0.9701 |
| max_accuracy | 0.9457 |
| max_accuracy_threshold | 9.7874 |
| max_f1 | 0.9555 |
| max_f1_threshold | 9.7874 |
| max_precision | 0.92 |
| max_recall | 0.9938 |
| **max_ap** | **0.9701** |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 2,752 training samples
* Columns: sentence2
, label
, and sentence1
* Approximate statistics based on the first 1000 samples:
| | sentence2 | label | sentence1 |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | int | string |
| details |
What are the ingredients of pizza?
| 1
| What are the ingredients of a pizza?
|
| What are the ingredients of a burger?
| 0
| What are the ingredients of a pizza?
|
| How is photosynthesis carried out?
| 1
| How does photosynthesis work?
|
* Loss: [OnlineContrastiveLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
### Evaluation Dataset
#### Unnamed Dataset
* Size: 276 evaluation samples
* Columns: sentence2
, label
, and sentence1
* Approximate statistics based on the first 276 samples:
| | sentence2 | label | sentence1 |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | int | string |
| details | How is AI used to enhance cybersecurity?
| 0
| What are the challenges of AI in cybersecurity?
|
| The SYSTEM log documentation can be accessed by clicking on the link which will take you to the main version.
| 1
| You can find the SYSTEM log documentation on the main version. Click on the provided link to redirect to the main version of the documentation.
|
| Name the capital city of Italy
| 1
| What is the capital of Italy?
|
* Loss: [OnlineContrastiveLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `gradient_accumulation_steps`: 2
- `num_train_epochs`: 4
- `warmup_ratio`: 0.1
- `load_best_model_at_end`: True
- `optim`: adamw_torch_fused
- `batch_sampler`: no_duplicates
#### All Hyperparameters