SentenceTransformer based on google-bert/bert-base-cased

This is a sentence-transformers model finetuned from google-bert/bert-base-cased on the csv dataset. 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: google-bert/bert-base-cased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • csv

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, 'architecture': '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("cafierom/5Epoch_905_Statin_Contrastive")
# Run inference
sentences = [
    'COc1cc(CN(C)C(=O)c2nn(c(OC[C@@H](O)C[C@@H](O)CC(O)=O)c2C(C)C)-c2ccc(F)cc2)cc(OC)c1',
    'CC(C)c1sc(c(C2CCCC2)c1\\C=C\\[C@@H](O)C[C@@H](O)CC([O-])=O)-c1ccccc1',
    'CC(C)[C@H](NC(=O)[C@H](Cc1ccc(O)cc1)NC(=O)CNC(=O)[C@H](Cc1ccccc1)NC(=O)CN)C(=O)N[C@@H](C)C(=O)N[C@@H](CCC(O)=O)C(O)=O',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.2038, 0.4376],
#         [0.2038, 1.0000, 0.9656],
#         [0.4376, 0.9656, 1.0000]])

Training Details

Training Dataset

csv

• Dataset: csv
• Size: 148,695 training samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 23 tokensmean: 67.64 tokensmax: 145 tokens	min: 23 tokensmean: 65.13 tokensmax: 126 tokens	0: ~52.20%2: ~47.80%

• Samples:

  premise	hypothesis	label
  Cc1cc(-c2ccc(Cl)cc2)c(\C=C[C@@H]2CC@@HCC(=O)O2)c(C)n1	CCC@HC(=O)O[C@H]1CC@@HC=C2C=CC@HC@H[C@@H]12	2
  CC(C)c1c(OCC@@HCC@@HCC(O)=O)n(nc1C(=O)NCc1ccccc1C)-c1ccc(F)cc1	CCOC(=O)c1c(C(C)C)n(CC[C@@H]2CC@@HCC(=O)O2)c(c1-c1ccccc1)-c1ccccc1	0
  CCC@HC(=O)O[C@H]1CCC=C2C=CC@HC@H[C@@H]12	CC(c1ccc(F)cc1)c1cc(C)cc(C)c1OCC(O)CC@@HCC([O-])=O	0

• Loss: SoftmaxLoss

Evaluation Dataset

csv

• Dataset: csv
• Size: 26,241 evaluation samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 23 tokensmean: 67.34 tokensmax: 145 tokens	min: 23 tokensmean: 65.76 tokensmax: 145 tokens	0: ~52.90%2: ~47.10%

• Samples:

  premise	hypothesis	label
  CC(C)n1c(CCC@@HCC@@HCC([O-])=O)c(-c2ccc(F)cc2)c2c1c(=O)n(-c1ccccc1)c1ccccc21	C[C@@H]1CC(OC(=O)NCCCCCCCCCCC(=O)NC@@HC(C)(C)C)[C@@H]2C@@HC@@HC=CC2=C1	2
  CCC@HC(=O)O[C@H]1CC@@HC[C@@H]2C=CC@HC@H[C@@H]12	CC(C)c1sc(c(C2CCCC2)c1\C=C[C@@H](O)CC@@HCC([O-])=O)-c1ccccc1	0
  CC(C)c1c(OCC@@HCC@@HCC(O)=O)n(nc1C(=O)NCc1ccccc1C)-c1ccc(F)cc1	CCC@HC(=O)O[C@H]1CCC=C2C=CC@HC@HC12	0

• Loss: SoftmaxLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• weight_decay: 0.01
• num_train_epochs: 5
• warmup_steps: 100
• fp16: True

All Hyperparameters

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• warmup_steps: 100
• 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}
• parallelism_config: 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: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• 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
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.0
• Transformers: 4.56.0
• PyTorch: 2.8.0+cu126
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.22.0

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@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",
}