Edit model card

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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/bge-base-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

Metric Value
cosine_accuracy@1 0.8529
cosine_accuracy@3 0.9264
cosine_accuracy@5 0.9463
cosine_accuracy@10 0.959
cosine_precision@1 0.8529
cosine_precision@3 0.3088
cosine_precision@5 0.1893
cosine_precision@10 0.0959
cosine_recall@1 0.8529
cosine_recall@3 0.9264
cosine_recall@5 0.9463
cosine_recall@10 0.959
cosine_ndcg@10 0.9106
cosine_mrr@10 0.8946
cosine_map@100 0.896

Information Retrieval

Metric Value
cosine_accuracy@1 0.8472
cosine_accuracy@3 0.9321
cosine_accuracy@5 0.9477
cosine_accuracy@10 0.9604
cosine_precision@1 0.8472
cosine_precision@3 0.3107
cosine_precision@5 0.1895
cosine_precision@10 0.096
cosine_recall@1 0.8472
cosine_recall@3 0.9321
cosine_recall@5 0.9477
cosine_recall@10 0.9604
cosine_ndcg@10 0.9095
cosine_mrr@10 0.8926
cosine_map@100 0.8939

Information Retrieval

Metric Value
cosine_accuracy@1 0.8359
cosine_accuracy@3 0.925
cosine_accuracy@5 0.9406
cosine_accuracy@10 0.9533
cosine_precision@1 0.8359
cosine_precision@3 0.3083
cosine_precision@5 0.1881
cosine_precision@10 0.0953
cosine_recall@1 0.8359
cosine_recall@3 0.925
cosine_recall@5 0.9406
cosine_recall@10 0.9533
cosine_ndcg@10 0.9004
cosine_mrr@10 0.8828
cosine_map@100 0.884

Information Retrieval

Metric Value
cosine_accuracy@1 0.8175
cosine_accuracy@3 0.9109
cosine_accuracy@5 0.9264
cosine_accuracy@10 0.9434
cosine_precision@1 0.8175
cosine_precision@3 0.3036
cosine_precision@5 0.1853
cosine_precision@10 0.0943
cosine_recall@1 0.8175
cosine_recall@3 0.9109
cosine_recall@5 0.9264
cosine_recall@10 0.9434
cosine_ndcg@10 0.8863
cosine_mrr@10 0.8674
cosine_map@100 0.8687

Information Retrieval

Metric Value
cosine_accuracy@1 0.7779
cosine_accuracy@3 0.8868
cosine_accuracy@5 0.9066
cosine_accuracy@10 0.9208
cosine_precision@1 0.7779
cosine_precision@3 0.2956
cosine_precision@5 0.1813
cosine_precision@10 0.0921
cosine_recall@1 0.7779
cosine_recall@3 0.8868
cosine_recall@5 0.9066
cosine_recall@10 0.9208
cosine_ndcg@10 0.857
cosine_mrr@10 0.8358
cosine_map@100 0.8374

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: 63.38 tokens
    • max: 485 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 - 0.8674 0.8951 0.8991 0.8236 0.8996
1.2698 10 1.6285 - - - - -
1.9048 15 - 0.8662 0.8849 0.8951 0.8334 0.8945
2.5397 20 0.7273 - - - - -
2.9206 23 - 0.8681 0.8849 0.8946 0.8362 0.8967
3.5556 28 - 0.8687 0.884 0.8939 0.8374 0.896
  • 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}
}
Downloads last month
5
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for juanpablomesa/bge-base-bioasq-matryoshka

Finetuned
(253)
this model

Evaluation results