Hugging Face's logo

tomaarsen
/
stsb-distilbert-base-mnrl-cl-multi

Sentence Similarity
sentence-transformers
Safetensors
English
distilbert
feature-extraction
loss:MultipleNegativesRankingLoss
loss:ContrastiveLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
stsb-distilbert-base-mnrl-cl-multi / README.md
tomaarsen's picture
tomaarsen HF staff
Add new SentenceTransformer model.
ed25478 verified
preview code
|
raw
history blame contribute delete
41.4 kB
---
language:
- en
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- loss:MultipleNegativesRankingLoss
- loss:ContrastiveLoss
base_model: sentence-transformers/stsb-distilbert-base
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
- average_precision
- f1
- precision
- recall
- threshold
- 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
- dot_accuracy@1
- dot_accuracy@3
- dot_accuracy@5
- dot_accuracy@10
- dot_precision@1
- dot_precision@3
- dot_precision@5
- dot_precision@10
- dot_recall@1
- dot_recall@3
- dot_recall@5
- dot_recall@10
- dot_ndcg@10
- dot_mrr@10
- dot_map@100
widget:
- source_sentence: What is Mindset?
sentences:
- What is a mindset?
- Can you eat only once a day?
- Is law a good career choice?
- source_sentence: Is a queef real?
sentences:
- Is "G" based on real events?
- What is the entire court process?
- How do I reduce my weight?
- source_sentence: Is Cicret a scam?
sentences:
- Is the Cicret Bracelet a scam?
- Was World War II Inevitable?
- What are some of the best photos?
- source_sentence: What is Planet X?
sentences:
- Do planet X exist?
- What are the best C++ books?
- How can I lose my weight fast?
- source_sentence: How fast is fast?
sentences:
- How does light travel so fast?
- How do I copyright my books?
- What is a black hole made of?
pipeline_tag: sentence-similarity
co2_eq_emissions:
emissions: 32.724475965905576
energy_consumed: 0.08418911136527617
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
ram_total_size: 31.777088165283203
hours_used: 0.399
hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
- name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: quora duplicates
type: quora-duplicates
metrics:
- type: cosine_accuracy
value: 0.846
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.7969297170639038
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.7791495198902607
name: Cosine F1
- type: cosine_f1_threshold
value: 0.7139598727226257
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.6977886977886978
name: Cosine Precision
- type: cosine_recall
value: 0.8819875776397516
name: Cosine Recall
- type: cosine_ap
value: 0.8230449963294564
name: Cosine Ap
- type: dot_accuracy
value: 0.843
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 151.2908477783203
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.7660818713450294
name: Dot F1
- type: dot_f1_threshold
value: 143.77838134765625
name: Dot F1 Threshold
- type: dot_precision
value: 0.7237569060773481
name: Dot Precision
- type: dot_recall
value: 0.8136645962732919
name: Dot Recall
- type: dot_ap
value: 0.7946044629726107
name: Dot Ap
- type: manhattan_accuracy
value: 0.838
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 194.99119567871094
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.7704081632653061
name: Manhattan F1
- type: manhattan_f1_threshold
value: 247.49777221679688
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.6536796536796536
name: Manhattan Precision
- type: manhattan_recall
value: 0.937888198757764
name: Manhattan Recall
- type: manhattan_ap
value: 0.8149715271935773
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.841
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 9.02225112915039
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.7703889585947302
name: Euclidean F1
- type: euclidean_f1_threshold
value: 11.385245323181152
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.6463157894736842
name: Euclidean Precision
- type: euclidean_recall
value: 0.953416149068323
name: Euclidean Recall
- type: euclidean_ap
value: 0.8152967320117391
name: Euclidean Ap
- type: max_accuracy
value: 0.846
name: Max Accuracy
- type: max_accuracy_threshold
value: 194.99119567871094
name: Max Accuracy Threshold
- type: max_f1
value: 0.7791495198902607
name: Max F1
- type: max_f1_threshold
value: 247.49777221679688
name: Max F1 Threshold
- type: max_precision
value: 0.7237569060773481
name: Max Precision
- type: max_recall
value: 0.953416149068323
name: Max Recall
- type: max_ap
value: 0.8230449963294564
name: Max Ap
- task:
type: paraphrase-mining
name: Paraphrase Mining
dataset:
name: quora duplicates dev
type: quora-duplicates-dev
metrics:
- type: average_precision
value: 0.5888649029434471
name: Average Precision
- type: f1
value: 0.5761652140962487
name: F1
- type: precision
value: 0.5477552123204396
name: Precision
- type: recall
value: 0.6076834690513064
name: Recall
- type: threshold
value: 0.7728720009326935
name: Threshold
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy@1
value: 0.963
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9906
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9944
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9982
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.963
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.4285333333333333
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.27568000000000004
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.14494
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8299562338609103
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9590366552956846
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9806221849555673
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9925738410935468
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9784033087450696
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.9771579365079368
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.9709189650394419
name: Cosine Map@100
- type: dot_accuracy@1
value: 0.9514
name: Dot Accuracy@1
- type: dot_accuracy@3
value: 0.9852
name: Dot Accuracy@3
- type: dot_accuracy@5
value: 0.991
name: Dot Accuracy@5
- type: dot_accuracy@10
value: 0.9968
name: Dot Accuracy@10
- type: dot_precision@1
value: 0.9514
name: Dot Precision@1
- type: dot_precision@3
value: 0.4247333333333334
name: Dot Precision@3
- type: dot_precision@5
value: 0.27364
name: Dot Precision@5
- type: dot_precision@10
value: 0.14458000000000001
name: Dot Precision@10
- type: dot_recall@1
value: 0.8194380520427287
name: Dot Recall@1
- type: dot_recall@3
value: 0.9520212390452685
name: Dot Recall@3
- type: dot_recall@5
value: 0.9755502441186265
name: Dot Recall@5
- type: dot_recall@10
value: 0.9910547306614953
name: Dot Recall@10
- type: dot_ndcg@10
value: 0.9715023430522326
name: Dot Ndcg@10
- type: dot_mrr@10
value: 0.9692583333333334
name: Dot Mrr@10
- type: dot_map@100
value: 0.961739772177385
name: Dot Map@100
---
# SentenceTransformer based on sentence-transformers/stsb-distilbert-base
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) datasets. 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:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) <!-- at revision 82ad392c08f81be9be9bf065339670b23f2e1493 -->
- **Maximum Sequence Length:** 128 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Datasets:**
- [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
- [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
- **Language:** en
<!-- - **License:** Unknown -->
### 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': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(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("tomaarsen/stsb-distilbert-base-mnrl-cl-multi")
# Run inference
sentences = [
'How fast is fast?',
'How does light travel so fast?',
'How do I copyright my books?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings)
print(similarities.shape)
# [3, 3]
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
## Evaluation
### Metrics
#### Binary Classification
* Dataset: `quora-duplicates`
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:----------|
| cosine_accuracy | 0.846 |
| cosine_accuracy_threshold | 0.7969 |
| cosine_f1 | 0.7791 |
| cosine_f1_threshold | 0.714 |
| cosine_precision | 0.6978 |
| cosine_recall | 0.882 |
| cosine_ap | 0.823 |
| dot_accuracy | 0.843 |
| dot_accuracy_threshold | 151.2908 |
| dot_f1 | 0.7661 |
| dot_f1_threshold | 143.7784 |
| dot_precision | 0.7238 |
| dot_recall | 0.8137 |
| dot_ap | 0.7946 |
| manhattan_accuracy | 0.838 |
| manhattan_accuracy_threshold | 194.9912 |
| manhattan_f1 | 0.7704 |
| manhattan_f1_threshold | 247.4978 |
| manhattan_precision | 0.6537 |
| manhattan_recall | 0.9379 |
| manhattan_ap | 0.815 |
| euclidean_accuracy | 0.841 |
| euclidean_accuracy_threshold | 9.0223 |
| euclidean_f1 | 0.7704 |
| euclidean_f1_threshold | 11.3852 |
| euclidean_precision | 0.6463 |
| euclidean_recall | 0.9534 |
| euclidean_ap | 0.8153 |
| max_accuracy | 0.846 |
| max_accuracy_threshold | 194.9912 |
| max_f1 | 0.7791 |
| max_f1_threshold | 247.4978 |
| max_precision | 0.7238 |
| max_recall | 0.9534 |
| **max_ap** | **0.823** |
#### Paraphrase Mining
* Dataset: `quora-duplicates-dev`
* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator)
| Metric | Value |
|:----------------------|:-----------|
| **average_precision** | **0.5889** |
| f1 | 0.5762 |
| precision | 0.5478 |
| recall | 0.6077 |
| threshold | 0.7729 |
#### Information Retrieval
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.963 |
| cosine_accuracy@3 | 0.9906 |
| cosine_accuracy@5 | 0.9944 |
| cosine_accuracy@10 | 0.9982 |
| cosine_precision@1 | 0.963 |
| cosine_precision@3 | 0.4285 |
| cosine_precision@5 | 0.2757 |
| cosine_precision@10 | 0.1449 |
| cosine_recall@1 | 0.83 |
| cosine_recall@3 | 0.959 |
| cosine_recall@5 | 0.9806 |
| cosine_recall@10 | 0.9926 |
| cosine_ndcg@10 | 0.9784 |
| cosine_mrr@10 | 0.9772 |
| **cosine_map@100** | **0.9709** |
| dot_accuracy@1 | 0.9514 |
| dot_accuracy@3 | 0.9852 |
| dot_accuracy@5 | 0.991 |
| dot_accuracy@10 | 0.9968 |
| dot_precision@1 | 0.9514 |
| dot_precision@3 | 0.4247 |
| dot_precision@5 | 0.2736 |
| dot_precision@10 | 0.1446 |
| dot_recall@1 | 0.8194 |
| dot_recall@3 | 0.952 |
| dot_recall@5 | 0.9756 |
| dot_recall@10 | 0.9911 |
| dot_ndcg@10 | 0.9715 |
| dot_mrr@10 | 0.9693 |
| dot_map@100 | 0.9617 |
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Datasets
#### mnrl
* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
* Size: 100,000 training samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 13.85 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.65 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.76 tokens</li><li>max: 64 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|
| <code>Why in India do we not have one on one political debate as in USA?</code> | <code>Why cant we have a public debate between politicians in India like the one in US?</code> | <code>Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?</code> |
| <code>What is OnePlus One?</code> | <code>How is oneplus one?</code> | <code>Why is OnePlus One so good?</code> |
| <code>Does our mind control our emotions?</code> | <code>How do smart and successful people control their emotions?</code> | <code>How can I control my positive emotions for the people whom I love but they don't care about me?</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
#### cl
* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
* Size: 100,000 training samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 6 tokens</li><li>mean: 15.3 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.66 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------|
| <code>What is the step by step guide to invest in share market in india?</code> | <code>What is the step by step guide to invest in share market?</code> | <code>0</code> |
| <code>What is the story of Kohinoor (Koh-i-Noor) Diamond?</code> | <code>What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?</code> | <code>0</code> |
| <code>How can I increase the speed of my internet connection while using a VPN?</code> | <code>How can Internet speed be increased by hacking through DNS?</code> | <code>0</code> |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters:
```json
{
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
"margin": 0.5,
"size_average": true
}
```
### Evaluation Datasets
#### mnrl
* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
* Size: 1,000 evaluation samples
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 7 tokens</li><li>mean: 13.84 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.8 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.71 tokens</li><li>max: 56 tokens</li></ul> |
* Samples:
| anchor | positive | negative |
|:---------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Which programming language is best for developing low-end games?</code> | <code>What coding language should I learn first for making games?</code> | <code>I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages ​​I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms?</code> |
| <code>Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump?</code> | <code>Should Meryl Streep be using her position to attack the president?</code> | <code>Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?</code> |
| <code>Where can I found excellent commercial fridges in Sydney?</code> | <code>Where can I found impressive range of commercial fridges in Sydney?</code> | <code>What is the best grocery delivery service in Sydney?</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
#### cl
* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
* Size: 1,000 evaluation samples
* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | sentence1 | sentence2 | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 5 tokens</li><li>mean: 15.59 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>0: ~63.40%</li><li>1: ~36.60%</li></ul> |
* Samples:
| sentence1 | sentence2 | label |
|:--------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|:---------------|
| <code>What should I ask my friend to get from UK to India?</code> | <code>What is the process of getting a surgical residency in UK after completing MBBS from India?</code> | <code>0</code> |
| <code>How can I learn hacking for free?</code> | <code>How can I learn to hack seriously?</code> | <code>1</code> |
| <code>Which is the best website to learn programming language C++?</code> | <code>Which is the best website to learn C++ Programming language for free?</code> | <code>0</code> |
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters:
```json
{
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
"margin": 0.5,
"size_average": true
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: False
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 1
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: None
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | cl loss | mnrl loss | cosine_map@100 | quora-duplicates-dev_average_precision | quora-duplicates_max_ap |
|:------:|:----:|:-------------:|:-------:|:---------:|:--------------:|:--------------------------------------:|:-----------------------:|
| 0 | 0 | - | - | - | 0.9245 | 0.4200 | 0.6890 |
| 0.0320 | 100 | 0.1634 | - | - | - | - | - |
| 0.0640 | 200 | 0.1206 | - | - | - | - | - |
| 0.0800 | 250 | - | 0.0190 | 0.1469 | 0.9530 | 0.5068 | 0.7354 |
| 0.0960 | 300 | 0.1036 | - | - | - | - | - |
| 0.1280 | 400 | 0.0836 | - | - | - | - | - |
| 0.1599 | 500 | 0.0918 | 0.0180 | 0.1008 | 0.9553 | 0.5259 | 0.7643 |
| 0.1919 | 600 | 0.0784 | - | - | - | - | - |
| 0.2239 | 700 | 0.0656 | - | - | - | - | - |
| 0.2399 | 750 | - | 0.0177 | 0.0905 | 0.9593 | 0.5305 | 0.7686 |
| 0.2559 | 800 | 0.0593 | - | - | - | - | - |
| 0.2879 | 900 | 0.0534 | - | - | - | - | - |
| 0.3199 | 1000 | 0.0612 | 0.0161 | 0.0736 | 0.9642 | 0.5512 | 0.7881 |
| 0.3519 | 1100 | 0.0572 | - | - | - | - | - |
| 0.3839 | 1200 | 0.06 | - | - | - | - | - |
| 0.3999 | 1250 | - | 0.0158 | 0.0641 | 0.9649 | 0.5567 | 0.7983 |
| 0.4159 | 1300 | 0.0565 | - | - | - | - | - |
| 0.4479 | 1400 | 0.0565 | - | - | - | - | - |
| 0.4798 | 1500 | 0.0475 | 0.0154 | 0.0578 | 0.9645 | 0.5614 | 0.8062 |
| 0.5118 | 1600 | 0.0596 | - | - | - | - | - |
| 0.5438 | 1700 | 0.0509 | - | - | - | - | - |
| 0.5598 | 1750 | - | 0.0150 | 0.0525 | 0.9674 | 0.5762 | 0.8092 |
| 0.5758 | 1800 | 0.0403 | - | - | - | - | - |
| 0.6078 | 1900 | 0.0431 | - | - | - | - | - |
| 0.6398 | 2000 | 0.0481 | 0.0150 | 0.0531 | 0.9689 | 0.5824 | 0.8128 |
| 0.6718 | 2100 | 0.05 | - | - | - | - | - |
| 0.7038 | 2200 | 0.0468 | - | - | - | - | - |
| 0.7198 | 2250 | - | 0.0146 | 0.0486 | 0.9684 | 0.5756 | 0.8195 |
| 0.7358 | 2300 | 0.0436 | - | - | - | - | - |
| 0.7678 | 2400 | 0.0409 | - | - | - | - | - |
| 0.7997 | 2500 | 0.0391 | 0.0145 | 0.0454 | 0.9705 | 0.5822 | 0.8190 |
| 0.8317 | 2600 | 0.0412 | - | - | - | - | - |
| 0.8637 | 2700 | 0.0373 | - | - | - | - | - |
| 0.8797 | 2750 | - | 0.0143 | 0.0451 | 0.9705 | 0.5889 | 0.8229 |
| 0.8957 | 2800 | 0.0428 | - | - | - | - | - |
| 0.9277 | 2900 | 0.0419 | - | - | - | - | - |
| 0.9597 | 3000 | 0.0376 | 0.0143 | 0.0435 | 0.9709 | 0.5889 | 0.8230 |
| 0.9917 | 3100 | 0.0366 | - | - | - | - | - |
### Environmental Impact
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
- **Energy Consumed**: 0.084 kWh
- **Carbon Emitted**: 0.033 kg of CO2
- **Hours Used**: 0.399 hours
### Training Hardware
- **On Cloud**: No
- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
- **RAM Size**: 31.78 GB
### Framework Versions
- Python: 3.11.6
- Sentence Transformers: 3.0.0.dev0
- Transformers: 4.41.0.dev0
- PyTorch: 2.3.0+cu121
- Accelerate: 0.26.1
- Datasets: 2.18.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
#### ContrastiveLoss
```bibtex
@inproceedings{hadsell2006dimensionality,
author={Hadsell, R. and Chopra, S. and LeCun, Y.},
booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
title={Dimensionality Reduction by Learning an Invariant Mapping},
year={2006},
volume={2},
number={},
pages={1735-1742},
doi={10.1109/CVPR.2006.100}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->