|
---
|
|
language:
|
|
- en
|
|
library_name: sentence-transformers
|
|
tags:
|
|
- sentence-transformers
|
|
- sentence-similarity
|
|
- feature-extraction
|
|
- loss:OnlineContrastiveLoss
|
|
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: Why did he go MIA?
|
|
sentences:
|
|
- Why did Yahoo kill Konfabulator?
|
|
- Why do people get angry with me?
|
|
- What are the best waterproof guns?
|
|
- source_sentence: Who is a soulmate?
|
|
sentences:
|
|
- Is she the “One”?
|
|
- Who is Pakistan's biggest enemy?
|
|
- Will smoking weed help with my anxiety?
|
|
- source_sentence: Is this poem good?
|
|
sentences:
|
|
- Is my poem any good?
|
|
- How can I become a good speaker?
|
|
- What is feminism?
|
|
- source_sentence: Who invented Yoga?
|
|
sentences:
|
|
- How was yoga invented?
|
|
- Who owns this number 3152150252?
|
|
- What is Dynamics CRM Services?
|
|
- source_sentence: Is stretching bad?
|
|
sentences:
|
|
- Is stretching good for you?
|
|
- If i=0; what will i=i++ do to i?
|
|
- What is the Output of this C program ?
|
|
pipeline_tag: sentence-similarity
|
|
co2_eq_emissions:
|
|
emissions: 15.707175691967695
|
|
energy_consumed: 0.040409299905757354
|
|
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: 0.202
|
|
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: 0.86
|
|
name: Cosine Accuracy
|
|
- type: cosine_accuracy_threshold
|
|
value: 0.8104104995727539
|
|
name: Cosine Accuracy Threshold
|
|
- type: cosine_f1
|
|
value: 0.8250591016548463
|
|
name: Cosine F1
|
|
- type: cosine_f1_threshold
|
|
value: 0.7247534394264221
|
|
name: Cosine F1 Threshold
|
|
- type: cosine_precision
|
|
value: 0.7347368421052631
|
|
name: Cosine Precision
|
|
- type: cosine_recall
|
|
value: 0.9407008086253369
|
|
name: Cosine Recall
|
|
- type: cosine_ap
|
|
value: 0.887247904332921
|
|
name: Cosine Ap
|
|
- type: dot_accuracy
|
|
value: 0.828
|
|
name: Dot Accuracy
|
|
- type: dot_accuracy_threshold
|
|
value: 157.35491943359375
|
|
name: Dot Accuracy Threshold
|
|
- type: dot_f1
|
|
value: 0.7898550724637681
|
|
name: Dot F1
|
|
- type: dot_f1_threshold
|
|
value: 145.7113037109375
|
|
name: Dot F1 Threshold
|
|
- type: dot_precision
|
|
value: 0.7155361050328227
|
|
name: Dot Precision
|
|
- type: dot_recall
|
|
value: 0.8814016172506739
|
|
name: Dot Recall
|
|
- type: dot_ap
|
|
value: 0.8369433397850002
|
|
name: Dot Ap
|
|
- type: manhattan_accuracy
|
|
value: 0.868
|
|
name: Manhattan Accuracy
|
|
- type: manhattan_accuracy_threshold
|
|
value: 208.00347900390625
|
|
name: Manhattan Accuracy Threshold
|
|
- type: manhattan_f1
|
|
value: 0.8307692307692308
|
|
name: Manhattan F1
|
|
- type: manhattan_f1_threshold
|
|
value: 208.00347900390625
|
|
name: Manhattan F1 Threshold
|
|
- type: manhattan_precision
|
|
value: 0.7921760391198044
|
|
name: Manhattan Precision
|
|
- type: manhattan_recall
|
|
value: 0.8733153638814016
|
|
name: Manhattan Recall
|
|
- type: manhattan_ap
|
|
value: 0.8868217413983182
|
|
name: Manhattan Ap
|
|
- type: euclidean_accuracy
|
|
value: 0.867
|
|
name: Euclidean Accuracy
|
|
- type: euclidean_accuracy_threshold
|
|
value: 9.269388198852539
|
|
name: Euclidean Accuracy Threshold
|
|
- type: euclidean_f1
|
|
value: 0.8301404853128991
|
|
name: Euclidean F1
|
|
- type: euclidean_f1_threshold
|
|
value: 9.525729179382324
|
|
name: Euclidean F1 Threshold
|
|
- type: euclidean_precision
|
|
value: 0.7888349514563107
|
|
name: Euclidean Precision
|
|
- type: euclidean_recall
|
|
value: 0.876010781671159
|
|
name: Euclidean Recall
|
|
- type: euclidean_ap
|
|
value: 0.8884154240019244
|
|
name: Euclidean Ap
|
|
- type: max_accuracy
|
|
value: 0.868
|
|
name: Max Accuracy
|
|
- type: max_accuracy_threshold
|
|
value: 208.00347900390625
|
|
name: Max Accuracy Threshold
|
|
- type: max_f1
|
|
value: 0.8307692307692308
|
|
name: Max F1
|
|
- type: max_f1_threshold
|
|
value: 208.00347900390625
|
|
name: Max F1 Threshold
|
|
- type: max_precision
|
|
value: 0.7921760391198044
|
|
name: Max Precision
|
|
- type: max_recall
|
|
value: 0.9407008086253369
|
|
name: Max Recall
|
|
- type: max_ap
|
|
value: 0.8884154240019244
|
|
name: Max Ap
|
|
- task:
|
|
type: paraphrase-mining
|
|
name: Paraphrase Mining
|
|
dataset:
|
|
name: quora duplicates dev
|
|
type: quora-duplicates-dev
|
|
metrics:
|
|
- type: average_precision
|
|
value: 0.534436244125929
|
|
name: Average Precision
|
|
- type: f1
|
|
value: 0.5447997274541295
|
|
name: F1
|
|
- type: precision
|
|
value: 0.5311002514589362
|
|
name: Precision
|
|
- type: recall
|
|
value: 0.5592246590398161
|
|
name: Recall
|
|
- type: threshold
|
|
value: 0.8626040816307068
|
|
name: Threshold
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: Unknown
|
|
type: unknown
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.928
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.9712
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.9782
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 0.9874
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.928
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.4151333333333334
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.26656
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.14166
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.7993523853760618
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.9341884771405065
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.9560896250710075
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 0.9766088525134997
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.9516150309696244
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.9509392857142857
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.9390263696194139
|
|
name: Cosine Map@100
|
|
- type: dot_accuracy@1
|
|
value: 0.8926
|
|
name: Dot Accuracy@1
|
|
- type: dot_accuracy@3
|
|
value: 0.9518
|
|
name: Dot Accuracy@3
|
|
- type: dot_accuracy@5
|
|
value: 0.9658
|
|
name: Dot Accuracy@5
|
|
- type: dot_accuracy@10
|
|
value: 0.9768
|
|
name: Dot Accuracy@10
|
|
- type: dot_precision@1
|
|
value: 0.8926
|
|
name: Dot Precision@1
|
|
- type: dot_precision@3
|
|
value: 0.40273333333333333
|
|
name: Dot Precision@3
|
|
- type: dot_precision@5
|
|
value: 0.26076
|
|
name: Dot Precision@5
|
|
- type: dot_precision@10
|
|
value: 0.13882
|
|
name: Dot Precision@10
|
|
- type: dot_recall@1
|
|
value: 0.7679620996617761
|
|
name: Dot Recall@1
|
|
- type: dot_recall@3
|
|
value: 0.9105756956997251
|
|
name: Dot Recall@3
|
|
- type: dot_recall@5
|
|
value: 0.9402185219519044
|
|
name: Dot Recall@5
|
|
- type: dot_recall@10
|
|
value: 0.9623418143294613
|
|
name: Dot Recall@10
|
|
- type: dot_ndcg@10
|
|
value: 0.9263520741106431
|
|
name: Dot Ndcg@10
|
|
- type: dot_mrr@10
|
|
value: 0.9243020634920638
|
|
name: Dot Mrr@10
|
|
- type: dot_map@100
|
|
value: 0.9094019438194247
|
|
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 [sentence-transformers/quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) 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:** [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 Dataset:**
|
|
- [sentence-transformers/quora-duplicates](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-ocl")
|
|
# Run inference
|
|
sentences = [
|
|
'Is stretching bad?',
|
|
'Is stretching good for you?',
|
|
'If i=0; what will i=i++ do to i?',
|
|
]
|
|
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 | 0.86 |
|
|
| cosine_accuracy_threshold | 0.8104 |
|
|
| cosine_f1 | 0.8251 |
|
|
| cosine_f1_threshold | 0.7248 |
|
|
| cosine_precision | 0.7347 |
|
|
| cosine_recall | 0.9407 |
|
|
| cosine_ap | 0.8872 |
|
|
| dot_accuracy | 0.828 |
|
|
| dot_accuracy_threshold | 157.3549 |
|
|
| dot_f1 | 0.7899 |
|
|
| dot_f1_threshold | 145.7113 |
|
|
| dot_precision | 0.7155 |
|
|
| dot_recall | 0.8814 |
|
|
| dot_ap | 0.8369 |
|
|
| manhattan_accuracy | 0.868 |
|
|
| manhattan_accuracy_threshold | 208.0035 |
|
|
| manhattan_f1 | 0.8308 |
|
|
| manhattan_f1_threshold | 208.0035 |
|
|
| manhattan_precision | 0.7922 |
|
|
| manhattan_recall | 0.8733 |
|
|
| manhattan_ap | 0.8868 |
|
|
| euclidean_accuracy | 0.867 |
|
|
| euclidean_accuracy_threshold | 9.2694 |
|
|
| euclidean_f1 | 0.8301 |
|
|
| euclidean_f1_threshold | 9.5257 |
|
|
| euclidean_precision | 0.7888 |
|
|
| euclidean_recall | 0.876 |
|
|
| euclidean_ap | 0.8884 |
|
|
| max_accuracy | 0.868 |
|
|
| max_accuracy_threshold | 208.0035 |
|
|
| max_f1 | 0.8308 |
|
|
| max_f1_threshold | 208.0035 |
|
|
| max_precision | 0.7922 |
|
|
| max_recall | 0.9407 |
|
|
| **max_ap** | **0.8884** |
|
|
|
|
#### 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** | **0.5344** |
|
|
| f1 | 0.5448 |
|
|
| precision | 0.5311 |
|
|
| recall | 0.5592 |
|
|
| threshold | 0.8626 |
|
|
|
|
#### Information Retrieval
|
|
|
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
|
|
|
| Metric | Value |
|
|
|:--------------------|:----------|
|
|
| cosine_accuracy@1 | 0.928 |
|
|
| cosine_accuracy@3 | 0.9712 |
|
|
| cosine_accuracy@5 | 0.9782 |
|
|
| cosine_accuracy@10 | 0.9874 |
|
|
| cosine_precision@1 | 0.928 |
|
|
| cosine_precision@3 | 0.4151 |
|
|
| cosine_precision@5 | 0.2666 |
|
|
| cosine_precision@10 | 0.1417 |
|
|
| cosine_recall@1 | 0.7994 |
|
|
| cosine_recall@3 | 0.9342 |
|
|
| cosine_recall@5 | 0.9561 |
|
|
| cosine_recall@10 | 0.9766 |
|
|
| cosine_ndcg@10 | 0.9516 |
|
|
| cosine_mrr@10 | 0.9509 |
|
|
| **cosine_map@100** | **0.939** |
|
|
| dot_accuracy@1 | 0.8926 |
|
|
| dot_accuracy@3 | 0.9518 |
|
|
| dot_accuracy@5 | 0.9658 |
|
|
| dot_accuracy@10 | 0.9768 |
|
|
| dot_precision@1 | 0.8926 |
|
|
| dot_precision@3 | 0.4027 |
|
|
| dot_precision@5 | 0.2608 |
|
|
| dot_precision@10 | 0.1388 |
|
|
| dot_recall@1 | 0.768 |
|
|
| dot_recall@3 | 0.9106 |
|
|
| dot_recall@5 | 0.9402 |
|
|
| dot_recall@10 | 0.9623 |
|
|
| dot_ndcg@10 | 0.9264 |
|
|
| dot_mrr@10 | 0.9243 |
|
|
| dot_map@100 | 0.9094 |
|
|
|
|
<!--
|
|
## 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 Dataset
|
|
|
|
#### sentence-transformers/quora-duplicates
|
|
|
|
* Dataset: [sentence-transformers/quora-duplicates](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: 15.5 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.46 tokens</li><li>max: 78 tokens</li></ul> | <ul><li>0: ~64.10%</li><li>1: ~35.90%</li></ul> |
|
|
* Samples:
|
|
| sentence1 | sentence2 | label |
|
|
|:---------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------|
|
|
| <code>What are the best ecommerce blogs to do guest posts on about SEO to gain new clients?</code> | <code>Interested in being a guest blogger for an ecommerce marketing blog?</code> | <code>0</code> |
|
|
| <code>How do I learn Informatica online training?</code> | <code>What is Informatica online training?</code> | <code>0</code> |
|
|
| <code>What effects does marijuana use have on the flu?</code> | <code>What effects does Marijuana use have on the common cold?</code> | <code>0</code> |
|
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#onlinecontrastiveloss)
|
|
|
|
### Evaluation Dataset
|
|
|
|
#### sentence-transformers/quora-duplicates
|
|
|
|
* Dataset: [sentence-transformers/quora-duplicates](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: 6 tokens</li><li>mean: 15.82 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.91 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>0: ~62.90%</li><li>1: ~37.10%</li></ul> |
|
|
* Samples:
|
|
| sentence1 | sentence2 | label |
|
|
|:------------------------------------------------------|:---------------------------------------------------|:---------------|
|
|
| <code>How should I prepare for JEE Mains 2017?</code> | <code>How do I prepare for the JEE 2016?</code> | <code>0</code> |
|
|
| <code>What is the gate exam?</code> | <code>What is the GATE exam in engineering?</code> | <code>0</code> |
|
|
| <code>Where do IRS officers get posted?</code> | <code>Does IRS Officers get posted abroad?</code> | <code>0</code> |
|
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#onlinecontrastiveloss)
|
|
|
|
### 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 | loss | cosine_map@100 | quora-duplicates-dev_average_precision | quora-duplicates_max_ap |
|
|
|:------:|:----:|:-------------:|:------:|:--------------:|:--------------------------------------:|:-----------------------:|
|
|
| 0 | 0 | - | - | 0.9235 | 0.4200 | 0.7276 |
|
|
| 0.0640 | 100 | 2.5123 | - | - | - | - |
|
|
| 0.1280 | 200 | 2.0534 | - | - | - | - |
|
|
| 0.1599 | 250 | - | 1.7914 | 0.9127 | 0.4082 | 0.8301 |
|
|
| 0.1919 | 300 | 1.9505 | - | - | - | - |
|
|
| 0.2559 | 400 | 1.9836 | - | - | - | - |
|
|
| 0.3199 | 500 | 1.8462 | 1.5923 | 0.9190 | 0.4445 | 0.8688 |
|
|
| 0.3839 | 600 | 1.7734 | - | - | - | - |
|
|
| 0.4479 | 700 | 1.7918 | - | - | - | - |
|
|
| 0.4798 | 750 | - | 1.5461 | 0.9291 | 0.4943 | 0.8707 |
|
|
| 0.5118 | 800 | 1.6157 | - | - | - | - |
|
|
| 0.5758 | 900 | 1.7244 | - | - | - | - |
|
|
| 0.6398 | 1000 | 1.7322 | 1.5294 | 0.9309 | 0.5048 | 0.8808 |
|
|
| 0.7038 | 1100 | 1.6825 | - | - | - | - |
|
|
| 0.7678 | 1200 | 1.6823 | - | - | - | - |
|
|
| 0.7997 | 1250 | - | 1.4812 | 0.9351 | 0.5126 | 0.8865 |
|
|
| 0.8317 | 1300 | 1.5707 | - | - | - | - |
|
|
| 0.8957 | 1400 | 1.6145 | - | - | - | - |
|
|
| 0.9597 | 1500 | 1.5795 | 1.4705 | 0.9390 | 0.5344 | 0.8884 |
|
|
|
|
|
|
### Environmental Impact
|
|
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
|
|
- **Energy Consumed**: 0.040 kWh
|
|
- **Carbon Emitted**: 0.016 kg of CO2
|
|
- **Hours Used**: 0.202 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",
|
|
}
|
|
```
|
|
|
|
<!--
|
|
## 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.*
|
|
--> |
