juanpablomesa/bge-small-bioasq-1epochs-batch32

BGE small finetuned BIOASQ

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-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-small-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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-small-bioasq-1epochs-batch32")
# 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, 384]

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

Evaluation

Metrics

Information Retrieval

• Dataset: BAAI/bge-small-en-v1.5
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8416
cosine_accuracy@3	0.925
cosine_accuracy@5	0.942
cosine_accuracy@10	0.959
cosine_precision@1	0.8416
cosine_precision@3	0.3083
cosine_precision@5	0.1884
cosine_precision@10	0.0959
cosine_recall@1	0.8416
cosine_recall@3	0.925
cosine_recall@5	0.942
cosine_recall@10	0.959
cosine_ndcg@10	0.9047
cosine_mrr@10	0.8869
cosine_map@100	0.8878

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: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• 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: 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: 1
• 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: 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
• 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: 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: 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	BAAI/bge-small-en-v1.5_cosine_map@100
0.0794	10	0.5344	-
0.1587	20	0.4615	-
0.2381	30	0.301	-
0.3175	40	0.2169	-
0.3968	50	0.1053	-
0.4762	60	0.1432	-
0.5556	70	0.1589	-
0.6349	80	0.1458	-
0.7143	90	0.1692	-
0.7937	100	0.1664	-
0.8730	110	0.1252	-
0.9524	120	0.1243	-
1.0	126	-	0.8858
0.0794	10	0.1393	-
0.1587	20	0.1504	-
0.2381	30	0.1009	-
0.3175	40	0.0689	-
0.3968	50	0.0301	-
0.4762	60	0.0647	-
0.5556	70	0.0748	-
0.6349	80	0.0679	-
0.7143	90	0.1091	-
0.7937	100	0.0953	-
0.8730	110	0.089	-
0.9524	120	0.0758	-
1.0	126	-	0.8878
0.0794	10	0.092	-
0.1587	20	0.0748	-
0.2381	30	0.0392	-
0.3175	40	0.014	-
0.3968	50	0.0057	-
0.4762	60	0.0208	-
0.5556	70	0.0173	-
0.6349	80	0.0195	-
0.7143	90	0.0349	-
0.7937	100	0.0483	-
0.8730	110	0.0254	-
0.9524	120	0.0325	-
1.0	126	-	0.8883
1.0317	130	0.0582	-
1.1111	140	0.0475	-
1.1905	150	0.0325	-
1.2698	160	0.0058	-
1.3492	170	0.0054	-
1.4286	180	0.0047	-
1.5079	190	0.0076	-
1.5873	200	0.0091	-
1.6667	210	0.0232	-
1.7460	220	0.0147	-
1.8254	230	0.0194	-
1.9048	240	0.0186	-
1.9841	250	0.0141	-
2.0	252	-	0.8857
2.0635	260	0.037	-
2.1429	270	0.0401	-
2.2222	280	0.0222	-
2.3016	290	0.0134	-
2.3810	300	0.008	-
2.4603	310	0.0199	-
2.5397	320	0.017	-
2.6190	330	0.0164	-
2.6984	340	0.0344	-
2.7778	350	0.0352	-
2.8571	360	0.0346	-
2.9365	370	0.0256	-
3.0	378	-	0.8868
0.7937	100	0.0064	0.8878

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",
}

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}
}