tomaarsen/stsb-distilbert-base-quora-duplicate-questions

SentenceTransformer based on sentence-transformers/stsb-distilbert-base

This is a sentence-transformers model finetuned from sentence-transformers/stsb-distilbert-base. 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
• —Maximum Sequence Length: 128 tokens
• —Output Dimensionality: 768 tokens <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

Model Sources

• —Documentation: Sentence Transformers Documentation
• —Repository: Sentence Transformers on GitHub
• —Hugging Face: Sentence Transformers on Hugging Face

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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/stsb-distilbert-base-quora-duplicate-questions")
# Run inference
sentences = [
    "What is a fetish?",
    "What's a fetish?",
    "Is it good to read sex stories?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

<!--

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

• —Evaluated with <code>BinaryClassificationEvaluator</code>

Paraphrase Mining

• —Dataset: dev
• —Evaluated with <code>ParaphraseMiningEvaluator</code>

Information Retrieval

• —Evaluated with <code>InformationRetrievalEvaluator</code>

<!--

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

Unnamed Dataset

• —Size: 207,326 training samples
• —Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>label</code>
• —Approximate statistics based on the first 1000 samples: | | sentence0 | sentence1 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------| | type | string | string | int | | details | <ul><li>min: 6 tokens</li><li>mean: 13.75 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.74 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>1: ~100.00%</li></ul> |
• —Samples: | sentence0 | sentence1 | label | |:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------|:---------------| | <code>How do I improve writing skill by myself?</code> | <code>How can I improve writing skills?</code> | <code>1</code> | | <code>Is it best to switch to Node.js from PHP?</code> | <code>Should I switch to Node.js or continue using PHP?</code> | <code>1</code> | | <code>What do Hillary Clinton's supporters say when confronted with all her lies and scandals?</code> | <code>What do Clinton supporters say when confronted with her scandals such as the emails and 'Clinton Cash'?</code> | <code>1</code> |
• —Loss: <code>sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }

Training Hyperparameters

Non-Default Hyperparameters

• —perdevicetrainbatchsize: 64
• —perdeviceevalbatchsize: 64
• —numtrainepochs: 1
• —roundrobinsampler: True

All Hyperparameters

<details><summary>Click to expand</summary>

• —overwriteoutputdir: False
• —do_predict: False
• —predictionlossonly: False
• —perdevicetrainbatchsize: 64
• —perdeviceevalbatchsize: 64
• —pergputrainbatchsize: None
• —pergpuevalbatchsize: None
• —gradientaccumulationsteps: 1
• —evalaccumulationsteps: None
• —learning_rate: 5e-05
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —maxgradnorm: 1
• —numtrainepochs: 1
• —max_steps: -1
• —lrschedulertype: linear
• —lrschedulerkwargs: {}
• —warmup_ratio: 0.0
• —warmup_steps: 0
• —log_level: passive
• —loglevelreplica: warning
• —logoneach_node: True
• —loggingnaninf_filter: True
• —save_safetensors: True
• —saveoneach_node: False
• —saveonlymodel: False
• —no_cuda: False
• —use_cpu: False
• —usempsdevice: False
• —seed: 42
• —data_seed: None
• —jitmodeeval: False
• —use_ipex: False
• —bf16: False
• —fp16: False
• —fp16optlevel: O1
• —halfprecisionbackend: auto
• —bf16fulleval: False
• —fp16fulleval: False
• —tf32: None
• —local_rank: 0
• —ddp_backend: None
• —tpunumcores: None
• —tpumetricsdebug: False
• —debug: []
• —dataloaderdroplast: False
• —dataloadernumworkers: 0
• —dataloaderprefetchfactor: None
• —past_index: -1
• —disable_tqdm: False
• —removeunusedcolumns: True
• —label_names: None
• —loadbestmodelatend: False
• —ignoredataskip: False
• —fsdp: []
• —fsdpminnum_params: 0
• —fsdpconfig: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgradckpt': False}
• —fsdptransformerlayerclsto_wrap: None
• —acceleratorconfig: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True}
• —deepspeed: None
• —labelsmoothingfactor: 0.0
• —optim: adamw_torch
• —optim_args: None
• —adafactor: False
• —groupbylength: False
• —lengthcolumnname: length
• —ddpfindunused_parameters: None
• —ddpbucketcap_mb: None
• —ddpbroadcastbuffers: None
• —dataloaderpinmemory: True
• —dataloaderpersistentworkers: False
• —skipmemorymetrics: True
• —uselegacyprediction_loop: False
• —pushtohub: False
• —resumefromcheckpoint: None
• —hubmodelid: None
• —hubstrategy: everysave
• —hubprivaterepo: False
• —hubalwayspush: False
• —gradient_checkpointing: False
• —gradientcheckpointingkwargs: None
• —includeinputsfor_metrics: False
• —fp16_backend: auto
• —pushtohubmodelid: None
• —pushtohub_organization: None
• —mp_parameters:
• —autofindbatch_size: False
• —full_determinism: False
• —torchdynamo: None
• —ray_scope: last
• —ddp_timeout: 1800
• —torch_compile: False
• —torchcompilebackend: None
• —torchcompilemode: None
• —dispatch_batches: None
• —split_batches: None
• —includetokensper_second: False
• —includenuminputtokensseen: False
• —neftunenoisealpha: None
• —optimtargetmodules: None
• —roundrobinsampler: True

</details>

Training Logs

Framework Versions

• —Python: 3.11.6
• —Sentence Transformers: 2.7.0.dev0
• —Transformers: 4.39.3
• —PyTorch: 2.1.0+cu121
• —Accelerate: 0.26.1
• —Datasets: 2.18.0
• —Tokenizers: 0.15.2

Citation

BibTeX

Sentence Transformers

@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

@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. -->