juanpablomesa/all-mpnet-base-v2-bioasq-matryoshka

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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/all-mpnet-base-v2
• Maximum Sequence Length: 384 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (2): Normalize()
)

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("juanpablomesa/all-mpnet-base-v2-bioasq-matryoshka")
# Run inference
sentences = [
    'Multicluster Pcdh diversity is required for mouse olfactory neural circuit assembly. The vertebrate clustered protocadherin (Pcdh) cell surface proteins are encoded by three closely linked gene clusters (Pcdhα, Pcdhβ, and Pcdhγ). Although deletion of individual Pcdh clusters had subtle phenotypic consequences, the loss of all three clusters (tricluster deletion) led to a severe axonal arborization defect and loss of self-avoidance.',
    'What are the effects of the deletion of all three Pcdh clusters (tricluster deletion) in mice?',
    'How many periods of regulatory innovation led to the evolution of vertebrates?',
]
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	0.8373
cosine_accuracy@3	0.9307
cosine_accuracy@5	0.9448
cosine_accuracy@10	0.959
cosine_precision@1	0.8373
cosine_precision@3	0.3102
cosine_precision@5	0.189
cosine_precision@10	0.0959
cosine_recall@1	0.8373
cosine_recall@3	0.9307
cosine_recall@5	0.9448
cosine_recall@10	0.959
cosine_ndcg@10	0.9039
cosine_mrr@10	0.8855
cosine_map@100	0.8868

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8373
cosine_accuracy@3	0.9335
cosine_accuracy@5	0.9463
cosine_accuracy@10	0.9604
cosine_precision@1	0.8373
cosine_precision@3	0.3112
cosine_precision@5	0.1893
cosine_precision@10	0.096
cosine_recall@1	0.8373
cosine_recall@3	0.9335
cosine_recall@5	0.9463
cosine_recall@10	0.9604
cosine_ndcg@10	0.9045
cosine_mrr@10	0.8861
cosine_map@100	0.8871

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8289
cosine_accuracy@3	0.9222
cosine_accuracy@5	0.942
cosine_accuracy@10	0.9533
cosine_precision@1	0.8289
cosine_precision@3	0.3074
cosine_precision@5	0.1884
cosine_precision@10	0.0953
cosine_recall@1	0.8289
cosine_recall@3	0.9222
cosine_recall@5	0.942
cosine_recall@10	0.9533
cosine_ndcg@10	0.8963
cosine_mrr@10	0.8774
cosine_map@100	0.8787

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8091
cosine_accuracy@3	0.8996
cosine_accuracy@5	0.9208
cosine_accuracy@10	0.9406
cosine_precision@1	0.8091
cosine_precision@3	0.2999
cosine_precision@5	0.1842
cosine_precision@10	0.0941
cosine_recall@1	0.8091
cosine_recall@3	0.8996
cosine_recall@5	0.9208
cosine_recall@10	0.9406
cosine_ndcg@10	0.8795
cosine_mrr@10	0.8594
cosine_map@100	0.8609

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7694
cosine_accuracy@3	0.8614
cosine_accuracy@5	0.8868
cosine_accuracy@10	0.9081
cosine_precision@1	0.7694
cosine_precision@3	0.2871
cosine_precision@5	0.1774
cosine_precision@10	0.0908
cosine_recall@1	0.7694
cosine_recall@3	0.8614
cosine_recall@5	0.8868
cosine_recall@10	0.9081
cosine_ndcg@10	0.8416
cosine_mrr@10	0.82
cosine_map@100	0.8224

Training Details

Training Dataset

Unnamed Dataset

• Size: 4,012 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 3 tokens mean: 63.14 tokens max: 384 tokens	min: 5 tokens mean: 16.13 tokens max: 49 tokens

• Samples:

  positive	anchor
  Aberrant patterns of H3K4, H3K9, and H3K27 histone lysine methylation were shown to result in histone code alterations, which induce changes in gene expression, and affect the proliferation rate of cells in medulloblastoma.	What is the implication of histone lysine methylation in medulloblastoma?
  STAG1/STAG2 proteins are tumour suppressor proteins that suppress cell proliferation and are essential for differentiation.	What is the role of STAG1/STAG2 proteins in differentiation?
  The association between cell phone use and incident glioblastoma remains unclear. Some studies have reported that cell phone use was associated with incident glioblastoma, and with reduced survival of patients diagnosed with glioblastoma. However, other studies have repeatedly replicated to find an association between cell phone use and glioblastoma.	What is the association between cell phone use and glioblastoma?

• 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: 4
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• bf16: True
• tf32: True
• 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: 4
• 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: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: True
• 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
0.8889	7	-	0.8540	0.8752	0.8825	0.8050	0.8864
1.2698	10	1.2032	-	-	-	-	-
1.9048	15	-	0.8569	0.8775	0.8850	0.8169	0.8840
2.5397	20	0.5051	-	-	-	-	-
2.9206	23	-	0.861	0.8794	0.8866	0.8242	0.8858
3.5556	28	-	0.8609	0.8787	0.8871	0.8224	0.8868

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.5
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.31.0
• 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}
}