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

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: google-bert/bert-base-uncased
• Maximum Sequence Length: 75 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', '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("kwondw/bert-base-uncased-trec-covid-tsdae")
# Run inference
sentences = [
    'Of, cyclization using CF (3 CO))) ·Et (2) show that the, and enamidones trifluoromethyl residue were.',
    'Of particular interest, the Friedel–Crafts cyclization using (CF(3)CO)(2)O/BF(3)·Et(2)O show that near the expected keto-lactams, enamides and enamidones containing trifluoromethyl residue were isolated.',
    'FINDINGS: Initial clinical presentation included fever, chills, and myalgia in both patients, and for patient 1, diarrhoea.',
]
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, 0.7967, 0.4642],
#         [0.7967, 1.0000, 0.3914],
#         [0.4642, 0.3914, 1.0000]])

Evaluation

Metrics

Information Retrieval

• Dataset: trec-covid
• Evaluated with InformationRetrievalEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,204,106 training samples
• Columns: noisy and text
• Approximate statistics based on the first 1000 samples:

  	noisy	text
  type	string	string
  details	min: 3 tokensmean: 22.09 tokensmax: 75 tokens	min: 6 tokensmean: 34.99 tokensmax: 75 tokens

• Samples:

  noisy	text
  of the mobile apps can potentially help mobile app developers improve or modify their mobile app achieve optimal outcomes	The results of the mobile apps assessment can potentially help mobile app developers improve or modify their existing mobile app designs to achieve optimal outcomes.
  In model such specialty of covid-19 virus as the presence of "super-spreaders" by a on a hierarchic landscape of social spreads infection	In particular, our model describes such a specialty of spread of covid-19 virus as the presence of "super-spreaders" who by performing a kind of random walk on a hierarchic landscape of social clusters spreads infection.
  The SARS-CoV-2 result	The primary outcome was SARS-CoV-2 test result.

• Loss: DenoisingAutoEncoderLoss with these parameters:

  {
      "decoder_name_or_path": "google-bert/bert-base-uncased",
      "need_retokenization": false
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 10,000 evaluation samples
• Columns: noisy and text
• Approximate statistics based on the first 1000 samples:

  	noisy	text
  type	string	string
  details	min: 3 tokensmean: 21.7 tokensmax: 75 tokens	min: 4 tokensmean: 33.89 tokensmax: 75 tokens

• Samples:

  noisy	text
  The intraoperative hypertension and hypotension not the PHE non-PHE cohorts.	The frequency of intraoperative hypertension and hypotension did not differ between the PHE and non-PHE cohorts.
  , existing variants suffer problems: () large-scale optimization; (2) hyperparameter problem; high computational cost of the operations	However, the existing BSO variants can suffer from three problems: (1) large-scale optimization problem; (2) hyperparameter optimization problem; (3) high computational cost of the clustering operations.
  neurological impact of coronaviruses implications the novel SARS-CoV-2	Potential neurological impact of coronaviruses: implications for the novel SARS-CoV-2.

• Loss: DenoisingAutoEncoderLoss with these parameters:

  {
      "decoder_name_or_path": "google-bert/bert-base-uncased",
      "need_retokenization": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 3e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 3e-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: None
• 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
• 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: True
• 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
• project: huggingface
• trackio_space_id: trackio
• 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: no
• 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: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 3.9 hours
• Evaluation: 33.6 minutes
• Total: 4.5 hours

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.4.1
• Transformers: 4.57.6
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 5.0.0
• Tokenizers: 0.22.2

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",
}

DenoisingAutoEncoderLoss

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}