README.md

metadata

base_model: NeuML/pubmedbert-base-embeddings
datasets: []
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - 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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:530
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      If you receive a BharatPe speaker that you didn't order, please contact
      BharatPe support immediately. They will assist in resolving the issue and
      advise on the next steps.
    sentences:
      - Can I control multiple BharatPe speakers from one app?
      - >-
        What to do if the BharatPe speaker's transaction announcements are
        intermittently silent?
      - What should I do if I receive a BharatPe speaker without ordering it?
  - source_sentence: >-
      Remote control capabilities depend on the model of the BharatPe speaker.
      Check if your model supports remote control through the BharatPe app or a
      connected device.
    sentences:
      - How do I update my personal details in my Bharatpe account?
      - What are the benefits of the BharatPe speaker?
      - Can I control the BharatPe speaker remotely?
  - source_sentence: >-
      If the announcements are not clear, check the speaker's volume settings
      and ensure it's not placed near noisy equipment. If clarity doesn't
      improve, the speaker may need servicing.
    sentences:
      - >-
        What to do if my BharatPe speaker is not syncing with the transaction
        history in the app?
      - What should I do if the speaker is not announcing payments clearly?
      - The speaker doesn't produce any sound, what can be done?
  - source_sentence: >-
      If the speaker is causing interference, try relocating it or other devices
      to reduce the interference. Ensure there's a reasonable distance between
      the speaker and other wireless equipment.
    sentences:
      - Can I use my Bharatpe device for international transactions?
      - How do I know if my BharatPe speaker is under warranty?
      - >-
        What should I do if the BharatPe speaker is causing interference with
        other wireless devices?
  - source_sentence: >-
      I can understand and respond in multiple Indian regional languages. Feel
      free to communicate with me in the language you're most comfortable with.
    sentences:
      - How can I check if the BharatPe speaker is receiving a network signal?
      - Bharti, can you provide tips for effective online communication?
      - Bharti, what languages can you understand and respond to?
model-index:
  - name: pubmedbert-base-embedding Chatbot Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.7674418604651163
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9069767441860465
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9302325581395349
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9302325581395349
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7674418604651163
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3023255813953489
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18604651162790697
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09302325581395349
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7674418604651163
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9069767441860465
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9302325581395349
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9302325581395349
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8563596702043667
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8313953488372093
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8349894291754757
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6976744186046512
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8837209302325582
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9302325581395349
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9302325581395349
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6976744186046512
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29457364341085274
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18604651162790697
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09302325581395349
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6976744186046512
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8837209302325582
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9302325581395349
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9302325581395349
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8320432881662091
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7984496124031009
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8017447288993117
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.7906976744186046
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8837209302325582
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9069767441860465
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9069767441860465
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7906976744186046
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29457364341085274
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1813953488372093
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09069767441860466
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7906976744186046
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8837209302325582
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9069767441860465
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9069767441860465
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8533147922143328
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8352713178294573
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8392285023210497
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6744186046511628
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.813953488372093
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8837209302325582
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9069767441860465
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6744186046511628
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2713178294573643
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17674418604651165
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09069767441860466
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6744186046511628
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.813953488372093
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8837209302325582
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9069767441860465
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.794152105183587
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7575858250276855
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7600321150655651
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6046511627906976
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7441860465116279
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7906976744186046
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8604651162790697
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6046511627906976
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.24806201550387597
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15813953488372093
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08604651162790698
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6046511627906976
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7441860465116279
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7906976744186046
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8604651162790697
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7220252449949186
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6786083425618308
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6823125300680127
            name: Cosine Map@100

pubmedbert-base-embedding Chatbot Matryoshka

This is a sentence-transformers model finetuned from NeuML/pubmedbert-base-embeddings. 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: NeuML/pubmedbert-base-embeddings
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity
• Language: en
• License: apache-2.0

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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (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("MANMEET75/pubmedbert-base-embedding-Chatbot-Matryoshk")
# Run inference
sentences = [
    "I can understand and respond in multiple Indian regional languages. Feel free to communicate with me in the language you're most comfortable with.",
    'Bharti, what languages can you understand and respond to?',
    'Bharti, can you provide tips for effective online communication?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7674
cosine_accuracy@3	0.907
cosine_accuracy@5	0.9302
cosine_accuracy@10	0.9302
cosine_precision@1	0.7674
cosine_precision@3	0.3023
cosine_precision@5	0.186
cosine_precision@10	0.093
cosine_recall@1	0.7674
cosine_recall@3	0.907
cosine_recall@5	0.9302
cosine_recall@10	0.9302
cosine_ndcg@10	0.8564
cosine_mrr@10	0.8314
cosine_map@100	0.835

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6977
cosine_accuracy@3	0.8837
cosine_accuracy@5	0.9302
cosine_accuracy@10	0.9302
cosine_precision@1	0.6977
cosine_precision@3	0.2946
cosine_precision@5	0.186
cosine_precision@10	0.093
cosine_recall@1	0.6977
cosine_recall@3	0.8837
cosine_recall@5	0.9302
cosine_recall@10	0.9302
cosine_ndcg@10	0.832
cosine_mrr@10	0.7984
cosine_map@100	0.8017

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7907
cosine_accuracy@3	0.8837
cosine_accuracy@5	0.907
cosine_accuracy@10	0.907
cosine_precision@1	0.7907
cosine_precision@3	0.2946
cosine_precision@5	0.1814
cosine_precision@10	0.0907
cosine_recall@1	0.7907
cosine_recall@3	0.8837
cosine_recall@5	0.907
cosine_recall@10	0.907
cosine_ndcg@10	0.8533
cosine_mrr@10	0.8353
cosine_map@100	0.8392

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6744
cosine_accuracy@3	0.814
cosine_accuracy@5	0.8837
cosine_accuracy@10	0.907
cosine_precision@1	0.6744
cosine_precision@3	0.2713
cosine_precision@5	0.1767
cosine_precision@10	0.0907
cosine_recall@1	0.6744
cosine_recall@3	0.814
cosine_recall@5	0.8837
cosine_recall@10	0.907
cosine_ndcg@10	0.7942
cosine_mrr@10	0.7576
cosine_map@100	0.76

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6047
cosine_accuracy@3	0.7442
cosine_accuracy@5	0.7907
cosine_accuracy@10	0.8605
cosine_precision@1	0.6047
cosine_precision@3	0.2481
cosine_precision@5	0.1581
cosine_precision@10	0.086
cosine_recall@1	0.6047
cosine_recall@3	0.7442
cosine_recall@5	0.7907
cosine_recall@10	0.8605
cosine_ndcg@10	0.722
cosine_mrr@10	0.6786
cosine_map@100	0.6823

Training Details

Training Dataset

Unnamed Dataset

• Size: 530 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 12 tokens mean: 36.83 tokens max: 107 tokens	min: 7 tokens mean: 18.54 tokens max: 30 tokens

• Samples:

  positive	anchor
  BharatPe Speaker comes with the following benefits: - Helps you avoid payment fraud - Lightweight & Easy installation process - Compatible with SIM & GPRS connectivity - Comes with a battery, no hassle of constant charging - Available in 10 Languages - Cashback Offers - Free replacement To Know more and place an order, tap below http://bharatpe.in/speaker.	What are the benefits of the BharatPe speaker?
  BharatPe Speaker comes with the following benefits: - Helps you avoid payment fraud - Lightweight & Easy installation process - Compatible with SIM & GPRS connectivity - Comes with a battery, no hassle of constant charging - Available in 10 Languages - Cashback Offers - Free replacement To Know more and place an order, tap below http://bharatpe.in/speaker.	What advantages does the BharatPe speaker offer?
  BharatPe Speaker comes with the following benefits: - Helps you avoid payment fraud - Lightweight & Easy installation process - Compatible with SIM & GPRS connectivity - Comes with a battery, no hassle of constant charging - Available in 10 Languages - Cashback Offers - Free replacement To Know more and place an order, tap below http://bharatpe.in/speaker.	Can you outline the benefits of using the BharatPe speaker?

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 16
• learning_rate: 2e-05
• num_train_epochs: 10
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• tf32: False
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 16
• eval_accumulation_steps: None
• learning_rate: 2e-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: 10
• max_steps: -1
• lr_scheduler_type: cosine
• 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
• restore_callback_states_from_checkpoint: 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: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: False
• 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: True
• 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_fused
• 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: False
• 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_eval_metrics: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.9412	1	-	0.4829	0.5338	0.5921	0.3235	0.6100
1.8824	2	-	0.5767	0.6175	0.6588	0.4176	0.6793
2.8235	3	-	0.6337	0.6776	0.6979	0.5083	0.7263
3.7647	4	-	0.6588	0.7257	0.7297	0.5840	0.7612
4.7059	5	-	0.7049	0.7766	0.7643	0.6151	0.7902
5.6471	6	-	0.7374	0.8257	0.7890	0.6519	0.7956
6.5882	7	-	0.7573	0.8261	0.7912	0.6689	0.7978
7.5294	8	-	0.7590	0.8275	0.7958	0.6811	0.8233
8.4706	9	-	0.76	0.8392	0.7998	0.6823	0.8234
9.4118	10	4.944	0.7600	0.8392	0.8017	0.6823	0.8350

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.32.1
• Datasets: 2.19.1
• 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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}