pankajrajdeo/BioForge-bioformer-16L-genotype-phenotype

SentenceTransformer

This is a sentence-transformers model trained on the json dataset. 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
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("pankajrajdeo/BioForge-bioformer-16L-genotype-phenotype")
# Run inference
sentences = [
    'alpha-L-Fucp-(1->2)-alpha-D-Galp-(1->3)-D-GlcpNAc',
    'Fuc(a1-2)Gal(a1-3)GlcNAc',
    'CHEBI',
]
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: g2p_eval
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8699
cosine_accuracy@3	0.9226
cosine_accuracy@5	0.9421
cosine_accuracy@10	0.9632
cosine_precision@1	0.8699
cosine_precision@3	0.3504
cosine_precision@5	0.2177
cosine_precision@10	0.1123
cosine_recall@1	0.803
cosine_recall@3	0.9077
cosine_recall@5	0.9316
cosine_recall@10	0.9563
cosine_ndcg@10	0.9094
cosine_mrr@10	0.9007
cosine_map@100	0.8928

Training Details

Training Dataset

json

• Dataset: json
• Size: 545,701 training samples
• Columns: anchor, positive, source, and pair_type
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	source	pair_type
  type	string	string	string	string
  details	min: 3 tokens mean: 11.82 tokens max: 229 tokens	min: 3 tokens mean: 16.48 tokens max: 256 tokens	min: 3 tokens mean: 4.97 tokens max: 7 tokens	min: 3 tokens mean: 3.06 tokens max: 9 tokens

• Samples:

  anchor	positive	source	pair_type
  breast cancer type 2 susceptibility protein sequence variant L1776* (human)	breast cancer type 2 susceptibility protein (human)	PR	hierarchy
  Ovarian varices	Varices of ovary	SNOMED_CT	synonym
  11-Deoxycortisol [Mass/volume] in Serum or Plasma --evening specimen	11-Deoxycortisol Evening specimen, Blood	LOINC	synonym

• Loss: main.MultipleNegativesSymmetricMarginLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 512
• gradient_accumulation_steps: 4
• learning_rate: 2e-05
• num_train_epochs: 4
• lr_scheduler_type: cosine
• warmup_ratio: 0.05
• bf16: True
• dataloader_num_workers: 16
• load_best_model_at_end: True
• gradient_checkpointing: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 512
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 4
• eval_accumulation_steps: None
• torch_empty_cache_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: 0.05
• 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: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 16
• 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
• 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: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	g2p_eval_cosine_ndcg@10
0.3265	87	-	0.9054
0.3752	100	0.4177	-
0.6529	174	-	0.9055
0.7505	200	0.4129	-
0.9794	261	-	0.9062
1.1238	300	0.4061	-
1.3039	348	-	0.9066
1.4991	400	0.3917	-
1.6304	435	-	0.9065
1.8743	500	0.3939	-
1.9568	522	-	0.9079
2.2477	600	0.3826	-
2.2814	609	-	0.9079
2.6079	696	-	0.9083
2.6229	700	0.3739	-
2.9343	783	-	0.9090
2.9981	800	0.3805	-
3.2589	870	-	0.9090
3.3715	900	0.3685	-
3.5854	957	-	0.9092
3.7467	1000	0.3701	-
3.9118	1044	-	0.9094

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.53.2
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.2
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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",
}