|
---
|
|
language:
|
|
- en
|
|
library_name: sentence-transformers
|
|
tags:
|
|
- sentence-transformers
|
|
- sentence-similarity
|
|
- feature-extraction
|
|
- loss:MultipleNegativesRankingLoss
|
|
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: How metro works?
|
|
sentences:
|
|
- How can Turing machine works?
|
|
- What are the best C++ books?
|
|
- What should I learn first in PHP?
|
|
- source_sentence: How fast is fast?
|
|
sentences:
|
|
- How does light travel so fast?
|
|
- How could I become an actor?
|
|
- Was Muhammad a pedophile?
|
|
- source_sentence: What is a kernel?
|
|
sentences:
|
|
- What is a tensor?
|
|
- What does copyright protect?
|
|
- Can we increase height after 23?
|
|
- source_sentence: What is a tensor?
|
|
sentences:
|
|
- What is reliance jio?
|
|
- What are the reasons of war?
|
|
- Does speed reading really work?
|
|
- source_sentence: Is Cicret a scam?
|
|
sentences:
|
|
- Is the Cicret Bracelet a scam?
|
|
- Can you eat only once a day?
|
|
- What books should every man read?
|
|
pipeline_tag: sentence-similarity
|
|
co2_eq_emissions:
|
|
emissions: 15.153912802318576
|
|
energy_consumed: 0.038985939877640395
|
|
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: 0.169
|
|
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: 0.816
|
|
name: Cosine Accuracy
|
|
- type: cosine_accuracy_threshold
|
|
value: 0.7866689562797546
|
|
name: Cosine Accuracy Threshold
|
|
- type: cosine_f1
|
|
value: 0.7285714285714286
|
|
name: Cosine F1
|
|
- type: cosine_f1_threshold
|
|
value: 0.735264778137207
|
|
name: Cosine F1 Threshold
|
|
- type: cosine_precision
|
|
value: 0.6746031746031746
|
|
name: Cosine Precision
|
|
- type: cosine_recall
|
|
value: 0.7919254658385093
|
|
name: Cosine Recall
|
|
- type: cosine_ap
|
|
value: 0.7731120768804719
|
|
name: Cosine Ap
|
|
- type: dot_accuracy
|
|
value: 0.807
|
|
name: Dot Accuracy
|
|
- type: dot_accuracy_threshold
|
|
value: 150.97946166992188
|
|
name: Dot Accuracy Threshold
|
|
- type: dot_f1
|
|
value: 0.7223796033994335
|
|
name: Dot F1
|
|
- type: dot_f1_threshold
|
|
value: 137.3444366455078
|
|
name: Dot F1 Threshold
|
|
- type: dot_precision
|
|
value: 0.6640625
|
|
name: Dot Precision
|
|
- type: dot_recall
|
|
value: 0.7919254658385093
|
|
name: Dot Recall
|
|
- type: dot_ap
|
|
value: 0.749212069604305
|
|
name: Dot Ap
|
|
- type: manhattan_accuracy
|
|
value: 0.81
|
|
name: Manhattan Accuracy
|
|
- type: manhattan_accuracy_threshold
|
|
value: 195.88662719726562
|
|
name: Manhattan Accuracy Threshold
|
|
- type: manhattan_f1
|
|
value: 0.7246376811594203
|
|
name: Manhattan F1
|
|
- type: manhattan_f1_threshold
|
|
value: 237.68594360351562
|
|
name: Manhattan F1 Threshold
|
|
- type: manhattan_precision
|
|
value: 0.6292906178489702
|
|
name: Manhattan Precision
|
|
- type: manhattan_recall
|
|
value: 0.8540372670807453
|
|
name: Manhattan Recall
|
|
- type: manhattan_ap
|
|
value: 0.7610544151599187
|
|
name: Manhattan Ap
|
|
- type: euclidean_accuracy
|
|
value: 0.81
|
|
name: Euclidean Accuracy
|
|
- type: euclidean_accuracy_threshold
|
|
value: 8.773942947387695
|
|
name: Euclidean Accuracy Threshold
|
|
- type: euclidean_f1
|
|
value: 0.7260812581913498
|
|
name: Euclidean F1
|
|
- type: euclidean_f1_threshold
|
|
value: 10.843769073486328
|
|
name: Euclidean F1 Threshold
|
|
- type: euclidean_precision
|
|
value: 0.6281179138321995
|
|
name: Euclidean Precision
|
|
- type: euclidean_recall
|
|
value: 0.860248447204969
|
|
name: Euclidean Recall
|
|
- type: euclidean_ap
|
|
value: 0.7611533877712096
|
|
name: Euclidean Ap
|
|
- type: max_accuracy
|
|
value: 0.816
|
|
name: Max Accuracy
|
|
- type: max_accuracy_threshold
|
|
value: 195.88662719726562
|
|
name: Max Accuracy Threshold
|
|
- type: max_f1
|
|
value: 0.7285714285714286
|
|
name: Max F1
|
|
- type: max_f1_threshold
|
|
value: 237.68594360351562
|
|
name: Max F1 Threshold
|
|
- type: max_precision
|
|
value: 0.6746031746031746
|
|
name: Max Precision
|
|
- type: max_recall
|
|
value: 0.860248447204969
|
|
name: Max Recall
|
|
- type: max_ap
|
|
value: 0.7731120768804719
|
|
name: Max Ap
|
|
- task:
|
|
type: paraphrase-mining
|
|
name: Paraphrase Mining
|
|
dataset:
|
|
name: quora duplicates dev
|
|
type: quora-duplicates-dev
|
|
metrics:
|
|
- type: average_precision
|
|
value: 0.5348666252858723
|
|
name: Average Precision
|
|
- type: f1
|
|
value: 0.5395064090300363
|
|
name: F1
|
|
- type: precision
|
|
value: 0.5174549291251892
|
|
name: Precision
|
|
- type: recall
|
|
value: 0.5635210071439276
|
|
name: Recall
|
|
- type: threshold
|
|
value: 0.762035459280014
|
|
name: Threshold
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: Unknown
|
|
type: unknown
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.9646
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.9926
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.9956
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 0.9986
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.9646
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.4293333333333333
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.2754
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.14515999999999998
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.830104138622815
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.9609072390452685
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.9808022997296821
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 0.9934541226453286
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.9795490191788223
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.9789640476190478
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.971751123151301
|
|
name: Cosine Map@100
|
|
- type: dot_accuracy@1
|
|
value: 0.9574
|
|
name: Dot Accuracy@1
|
|
- type: dot_accuracy@3
|
|
value: 0.9876
|
|
name: Dot Accuracy@3
|
|
- type: dot_accuracy@5
|
|
value: 0.9924
|
|
name: Dot Accuracy@5
|
|
- type: dot_accuracy@10
|
|
value: 0.9978
|
|
name: Dot Accuracy@10
|
|
- type: dot_precision@1
|
|
value: 0.9574
|
|
name: Dot Precision@1
|
|
- type: dot_precision@3
|
|
value: 0.4257333333333334
|
|
name: Dot Precision@3
|
|
- type: dot_precision@5
|
|
value: 0.27368000000000003
|
|
name: Dot Precision@5
|
|
- type: dot_precision@10
|
|
value: 0.14468000000000003
|
|
name: Dot Precision@10
|
|
- type: dot_recall@1
|
|
value: 0.8237692901379665
|
|
name: Dot Recall@1
|
|
- type: dot_recall@3
|
|
value: 0.9538191510221804
|
|
name: Dot Recall@3
|
|
- type: dot_recall@5
|
|
value: 0.9764249670623496
|
|
name: Dot Recall@5
|
|
- type: dot_recall@10
|
|
value: 0.9918117957075603
|
|
name: Dot Recall@10
|
|
- type: dot_ndcg@10
|
|
value: 0.9740754474178193
|
|
name: Dot Ndcg@10
|
|
- type: dot_mrr@10
|
|
value: 0.9731360317460321
|
|
name: Dot Mrr@10
|
|
- type: dot_map@100
|
|
value: 0.9646398037726347
|
|
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-mnrl")
|
|
# Run inference
|
|
sentences = [
|
|
'Is Cicret a scam?',
|
|
'Is the Cicret Bracelet a scam?',
|
|
'Can you eat only once a day?',
|
|
]
|
|
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 | 0.816 |
|
|
| cosine_accuracy_threshold | 0.7867 |
|
|
| cosine_f1 | 0.7286 |
|
|
| cosine_f1_threshold | 0.7353 |
|
|
| cosine_precision | 0.6746 |
|
|
| cosine_recall | 0.7919 |
|
|
| cosine_ap | 0.7731 |
|
|
| dot_accuracy | 0.807 |
|
|
| dot_accuracy_threshold | 150.9795 |
|
|
| dot_f1 | 0.7224 |
|
|
| dot_f1_threshold | 137.3444 |
|
|
| dot_precision | 0.6641 |
|
|
| dot_recall | 0.7919 |
|
|
| dot_ap | 0.7492 |
|
|
| manhattan_accuracy | 0.81 |
|
|
| manhattan_accuracy_threshold | 195.8866 |
|
|
| manhattan_f1 | 0.7246 |
|
|
| manhattan_f1_threshold | 237.6859 |
|
|
| manhattan_precision | 0.6293 |
|
|
| manhattan_recall | 0.854 |
|
|
| manhattan_ap | 0.7611 |
|
|
| euclidean_accuracy | 0.81 |
|
|
| euclidean_accuracy_threshold | 8.7739 |
|
|
| euclidean_f1 | 0.7261 |
|
|
| euclidean_f1_threshold | 10.8438 |
|
|
| euclidean_precision | 0.6281 |
|
|
| euclidean_recall | 0.8602 |
|
|
| euclidean_ap | 0.7612 |
|
|
| max_accuracy | 0.816 |
|
|
| max_accuracy_threshold | 195.8866 |
|
|
| max_f1 | 0.7286 |
|
|
| max_f1_threshold | 237.6859 |
|
|
| max_precision | 0.6746 |
|
|
| max_recall | 0.8602 |
|
|
| **max_ap** | **0.7731** |
|
|
|
|
#### 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** | **0.5349** |
|
|
| f1 | 0.5395 |
|
|
| precision | 0.5175 |
|
|
| recall | 0.5635 |
|
|
| threshold | 0.762 |
|
|
|
|
#### Information Retrieval
|
|
|
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
|
|
|
| Metric | Value |
|
|
|:--------------------|:-----------|
|
|
| cosine_accuracy@1 | 0.9646 |
|
|
| cosine_accuracy@3 | 0.9926 |
|
|
| cosine_accuracy@5 | 0.9956 |
|
|
| cosine_accuracy@10 | 0.9986 |
|
|
| cosine_precision@1 | 0.9646 |
|
|
| cosine_precision@3 | 0.4293 |
|
|
| cosine_precision@5 | 0.2754 |
|
|
| cosine_precision@10 | 0.1452 |
|
|
| cosine_recall@1 | 0.8301 |
|
|
| cosine_recall@3 | 0.9609 |
|
|
| cosine_recall@5 | 0.9808 |
|
|
| cosine_recall@10 | 0.9935 |
|
|
| cosine_ndcg@10 | 0.9795 |
|
|
| cosine_mrr@10 | 0.979 |
|
|
| **cosine_map@100** | **0.9718** |
|
|
| dot_accuracy@1 | 0.9574 |
|
|
| dot_accuracy@3 | 0.9876 |
|
|
| dot_accuracy@5 | 0.9924 |
|
|
| dot_accuracy@10 | 0.9978 |
|
|
| dot_precision@1 | 0.9574 |
|
|
| dot_precision@3 | 0.4257 |
|
|
| dot_precision@5 | 0.2737 |
|
|
| dot_precision@10 | 0.1447 |
|
|
| dot_recall@1 | 0.8238 |
|
|
| dot_recall@3 | 0.9538 |
|
|
| dot_recall@5 | 0.9764 |
|
|
| dot_recall@10 | 0.9918 |
|
|
| dot_ndcg@10 | 0.9741 |
|
|
| dot_mrr@10 | 0.9731 |
|
|
| dot_map@100 | 0.9646 |
|
|
|
|
<!--
|
|
## 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>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"
|
|
}
|
|
```
|
|
|
|
### 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>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"
|
|
}
|
|
```
|
|
|
|
### 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 | - | - | 0.9245 | 0.4200 | 0.6890 |
|
|
| 0.0640 | 100 | 0.2535 | - | - | - | - |
|
|
| 0.1280 | 200 | 0.1732 | - | - | - | - |
|
|
| 0.1599 | 250 | - | 0.1021 | 0.9601 | 0.5033 | 0.7342 |
|
|
| 0.1919 | 300 | 0.1465 | - | - | - | - |
|
|
| 0.2559 | 400 | 0.1186 | - | - | - | - |
|
|
| 0.3199 | 500 | 0.1159 | 0.0773 | 0.9653 | 0.5247 | 0.7453 |
|
|
| 0.3839 | 600 | 0.1088 | - | - | - | - |
|
|
| 0.4479 | 700 | 0.0993 | - | - | - | - |
|
|
| 0.4798 | 750 | - | 0.0665 | 0.9666 | 0.5264 | 0.7655 |
|
|
| 0.5118 | 800 | 0.0952 | - | - | - | - |
|
|
| 0.5758 | 900 | 0.0799 | - | - | - | - |
|
|
| 0.6398 | 1000 | 0.0855 | 0.0570 | 0.9709 | 0.5391 | 0.7717 |
|
|
| 0.7038 | 1100 | 0.0804 | - | - | - | - |
|
|
| 0.7678 | 1200 | 0.073 | - | - | - | - |
|
|
| 0.7997 | 1250 | - | 0.0513 | 0.9719 | 0.5329 | 0.7662 |
|
|
| 0.8317 | 1300 | 0.0741 | - | - | - | - |
|
|
| 0.8957 | 1400 | 0.0699 | - | - | - | - |
|
|
| 0.9597 | 1500 | 0.0755 | 0.0476 | 0.9718 | 0.5349 | 0.7731 |
|
|
|
|
|
|
### Environmental Impact
|
|
Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
|
|
- **Energy Consumed**: 0.039 kWh
|
|
- **Carbon Emitted**: 0.015 kg of CO2
|
|
- **Hours Used**: 0.169 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}
|
|
}
|
|
```
|
|
|
|
<!--
|
|
## 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.*
|
|
--> |
