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

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased on the stsb 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-uncased
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Training Dataset:
  • Language: en

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: 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("bingcheng9/bert-base-uncased-sts")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man sitting on the floor in a room is strumming a guitar.',
]
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

Semantic Similarity

Metric Value
pearson_cosine 0.8751
spearman_cosine 0.8764
pearson_manhattan 0.8501
spearman_manhattan 0.8544
pearson_euclidean 0.851
spearman_euclidean 0.8553
pearson_dot 0.8202
spearman_dot 0.823
pearson_max 0.8751
spearman_max 0.8764

Semantic Similarity

Metric Value
pearson_cosine 0.8489
spearman_cosine 0.8471
pearson_manhattan 0.8347
spearman_manhattan 0.8348
pearson_euclidean 0.8353
spearman_euclidean 0.8351
pearson_dot 0.7832
spearman_dot 0.7762
pearson_max 0.8489
spearman_max 0.8471

Training Details

Training Dataset

stsb

  • Dataset: stsb at ab7a5ac
  • Size: 5,749 training samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 score
    type string string float
    details
    • min: 6 tokens
    • mean: 10.0 tokens
    • max: 28 tokens
    • min: 5 tokens
    • mean: 9.95 tokens
    • max: 25 tokens
    • min: 0.0
    • mean: 0.54
    • max: 1.0
  • Samples:
    sentence1 sentence2 score
    A plane is taking off. An air plane is taking off. 1.0
    A man is playing a large flute. A man is playing a flute. 0.76
    A man is spreading shreded cheese on a pizza. A man is spreading shredded cheese on an uncooked pizza. 0.76
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    

Evaluation Dataset

stsb

  • Dataset: stsb at ab7a5ac
  • Size: 1,500 evaluation samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 score
    type string string float
    details
    • min: 5 tokens
    • mean: 15.1 tokens
    • max: 45 tokens
    • min: 6 tokens
    • mean: 15.11 tokens
    • max: 53 tokens
    • min: 0.0
    • mean: 0.47
    • max: 1.0
  • Samples:
    sentence1 sentence2 score
    A man with a hard hat is dancing. A man wearing a hard hat is dancing. 1.0
    A young child is riding a horse. A child is riding a horse. 0.95
    A man is feeding a mouse to a snake. The man is feeding a mouse to the snake. 1.0
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • num_train_epochs: 4
  • warmup_ratio: 0.1

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 16
  • 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
  • torch_empty_cache_steps: None
  • learning_rate: 5e-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: 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: 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: 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
  • eval_on_start: False
  • use_liger_kernel: False
  • eval_use_gather_object: False
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss loss sts-dev_spearman_cosine sts-test_spearman_cosine
0.2778 100 0.0608 0.0409 0.8190 -
0.5556 200 0.0338 0.0308 0.8457 -
0.8333 300 0.0286 0.0261 0.8605 -
1.1111 400 0.0215 0.0299 0.8639 -
1.3889 500 0.0144 0.0284 0.8714 -
1.6667 600 0.0131 0.0261 0.8670 -
1.9444 700 0.0133 0.0261 0.8714 -
2.2222 800 0.0082 0.0266 0.8727 -
2.5 900 0.0069 0.0257 0.8722 -
2.7778 1000 0.0064 0.0256 0.8731 -
3.0556 1100 0.006 0.0273 0.8746 -
3.3333 1200 0.0046 0.0262 0.8757 -
3.6111 1300 0.0042 0.0260 0.8760 -
3.8889 1400 0.0039 0.0257 0.8764 -
4.0 1440 - - - 0.8471

Framework Versions

  • Python: 3.12.4
  • Sentence Transformers: 3.1.1
  • Transformers: 4.45.2
  • PyTorch: 2.2.2
  • Accelerate: 0.26.0
  • Datasets: 3.0.2
  • Tokenizers: 0.20.1

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",
}
Downloads last month
18
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 bingcheng9/bert-base-uncased-sts

Finetuned
(2310)
this model

Dataset used to train bingcheng9/bert-base-uncased-sts

Evaluation results