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 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: 256 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity

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, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    '"Blood Effects" a mockumentary by film maker Kris Black, is a cross',
    'Title: Blood Effects. Genres: Comedy, Horror, Thriller. Keywords: mockumentary, filmmaking, found footage. Plot: "Blood Effects" a mockumentary by film maker Kris Black, is a cross between "Paranormal Activity" and Christopher Guest\'s "Best in Show". Presented as a "movie-within-a-movie", veteran Bruce Reisman produced Black\'s scathing satire of Hollywood horror movies, where reality ties itself up with fantasy, and the results are both humorous and horrifying.',
    'Title: Claydream. Genres: Documentary. Plot: A modern day Walt Disney, Will Vinton picked up a ball of clay and saw a world of potential. Known as the “Father of Claymation,” Vinton revolutionized the animation business during the 80s and 90s. But after 30 years of being the unheralded king of clay, Will Vinton’s carefully sculpted American dream came crumbling down.  Structured around interviews with this charismatic pioneer and his close collaborators, the film charts the rise and fall of the Academy Award and Emmy winning Will Vinton Studios.',
]
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, 0.8274, 0.0399],
#         [0.8274, 1.0000, 0.1651],
#         [0.0399, 0.1651, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 5,745 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 11 tokens
mean: 16.82 tokens
max: 31 tokens

min: 22 tokens
mean: 99.84 tokens
max: 256 tokens

	sentence_0	sentence_1
type	string	string
details	min: 11 tokens mean: 16.82 tokens max: 31 tokens	min: 22 tokens mean: 99.84 tokens max: 256 tokens

Samples:

sentence_0	sentence_1
`Set in a timeless mythical forest inhabited by fairies, goblins, unicorns and`	Title: Legend. Genres: Adventure, Fantasy. Keywords: witch, princess, monster, magic, winter, sword, hell, mythology, romance, snow, sorcerer, duel, devil, demon, evil, swashbuckler, unicorn, nostalgic, warrior, familiar. Plot: Set in a timeless mythical forest inhabited by fairies, goblins, unicorns and mortals, this fantastic story follows a mystical forest dweller, chosen by fate, to undertake a heroic quest. He must save the beautiful Princess Lili and defeat the demonic Lord of Darkness, or the world will be plunged into a never-ending ice age.
`After making their way through high school (twice), big changes are in`	Title: 22 Jump Street. Genres: Crime, Comedy, Action. Keywords: drug dealer, sarcasm, college, male friendship, sequel, undercover cop, buddy cop, buddy comedy, aftercreditsstinger, duringcreditsstinger, based on tv series. Plot: After making their way through high school (twice), big changes are in store for officers Schmidt and Jenko when they go deep undercover at a local college. But when Jenko meets a kindred spirit on the football team, and Schmidt infiltrates the bohemian art major scene, they begin to question their partnership. Now they don't have to just crack the case - they have to figure out if they can have a mature relationship. If these two overgrown adolescents can grow from freshmen into real men, college might be the best thing that ever happened to them.
`An upper-middle-class couple's life is destroyed when their only child is kidnapped`	`Title: The Tortured. Genres: Horror, Thriller. Keywords: husband wife relationship, loss of loved one, child murder, death of son. Plot: An upper-middle-class couple's life is destroyed when their only child is kidnapped and killed. Obsessed with revenge, the couple seizes an opportunity to kidnap the killer.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 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}
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: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
2.7778	500	0.2564

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.9.0+cu126
Accelerate: 1.11.0
Datasets: 4.0.0
Tokenizers: 0.22.1

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}
}