Hugging Face's logo

tomaarsen
/
stsb-distilbert-base-mnrl

Sentence Similarity
sentence-transformers
Safetensors
English
distilbert
feature-extraction
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
stsb-distilbert-base-mnrl / README.md
tomaarsen's picture
tomaarsen HF staff
Add new SentenceTransformer model.
f34c434 verified
preview code
|
raw
history blame contribute delete
32.7 kB
metadata
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 model finetuned from sentence-transformers/stsb-distilbert-base on the 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 Sources

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-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]

Evaluation

Metrics

Binary Classification

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

Metric Value
average_precision 0.5349
f1 0.5395
precision 0.5175
recall 0.5635
threshold 0.762

Information Retrieval

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

Training Details

Training Dataset

sentence-transformers/quora-duplicates

  • Dataset: sentence-transformers/quora-duplicates at 451a485
  • Size: 100,000 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 6 tokens
    • mean: 13.85 tokens
    • max: 42 tokens
    • min: 6 tokens
    • mean: 13.65 tokens
    • max: 44 tokens
    • min: 4 tokens
    • mean: 14.76 tokens
    • max: 64 tokens
  • Samples:
    anchor positive negative
    Why in India do we not have one on one political debate as in USA? Why cant we have a public debate between politicians in India like the one in US? Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?
    What is OnePlus One? How is oneplus one? Why is OnePlus One so good?
    Does our mind control our emotions? How do smart and successful people control their emotions? How can I control my positive emotions for the people whom I love but they don't care about me?
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

sentence-transformers/quora-duplicates

  • Dataset: sentence-transformers/quora-duplicates at 451a485
  • Size: 1,000 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 7 tokens
    • mean: 13.84 tokens
    • max: 43 tokens
    • min: 6 tokens
    • mean: 13.8 tokens
    • max: 38 tokens
    • min: 6 tokens
    • mean: 14.71 tokens
    • max: 56 tokens
  • Samples:
    anchor positive negative
    Which programming language is best for developing low-end games? What coding language should I learn first for making games? 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?
    Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump? Should Meryl Streep be using her position to attack the president? Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?
    Where can I found excellent commercial fridges in Sydney? Where can I found impressive range of commercial fridges in Sydney? What is the best grocery delivery service in Sydney?
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "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

Click to expand
  • 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

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.

  • 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 

@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}
}