metadata
language:
- en
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- loss:SoftmaxLoss
base_model: google-bert/bert-base-uncased
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
widget:
- source_sentence: the guy is dead
sentences:
- The dog is dead.
- The man is training the dog.
- People gather for an event.
- source_sentence: the boy is five
sentences:
- The girl is five years old.
- A man sits in a hotel lobby.
- The man is laying on the couch.
- source_sentence: a guy is waxing
sentences:
- A woman is making music.
- A girl is laying in the pool
- She is the boy's aunt.
- source_sentence: Dog herding cows
sentences:
- A woman is walking her dog.
- Both people are standing up.
- The women are friends.
- source_sentence: There is a party
sentences:
- people take pictures
- A man is repainting a garage
- the crew all ate lunch alone
pipeline_tag: sentence-similarity
co2_eq_emissions:
emissions: 3.4540412355858656
energy_consumed: 0.008886090721390334
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
ram_total_size: 31.777088165283203
hours_used: 0.049
hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
- name: SentenceTransformer based on google-bert/bert-base-uncased
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev
type: sts-dev
metrics:
- type: pearson_cosine
value: 0.5998264726332272
name: Pearson Cosine
- type: spearman_cosine
value: 0.6439392261876368
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6232915971361167
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6407370027700541
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6204725584722414
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6394239914170929
name: Spearman Euclidean
- type: pearson_dot
value: 0.4799617911944018
name: Pearson Dot
- type: spearman_dot
value: 0.4939854901099171
name: Spearman Dot
- type: pearson_max
value: 0.6232915971361167
name: Pearson Max
- type: spearman_max
value: 0.6439392261876368
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test
type: sts-test
metrics:
- type: pearson_cosine
value: 0.5516604742812986
name: Pearson Cosine
- type: spearman_cosine
value: 0.5840596347673308
name: Spearman Cosine
- type: pearson_manhattan
value: 0.5842488902993314
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.5886614741524346
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.582443715857982
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.5869827075201962
name: Spearman Euclidean
- type: pearson_dot
value: 0.4054565422297012
name: Pearson Dot
- type: spearman_dot
value: 0.40476618101346834
name: Spearman Dot
- type: pearson_max
value: 0.5842488902993314
name: Pearson Max
- type: spearman_max
value: 0.5886614741524346
name: Spearman Max
SentenceTransformer based on google-bert/bert-base-uncased
This is a sentence-transformers model finetuned from google-bert/bert-base-uncased on the sentence-transformers/all-nli 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
- 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}) 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("tomaarsen/bert-base-uncased-nli-v1")
# Run inference
sentences = [
'There is a party',
'people take pictures',
'A man is repainting a garage',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Semantic Similarity
- Dataset:
sts-dev
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.5998 |
spearman_cosine | 0.6439 |
pearson_manhattan | 0.6233 |
spearman_manhattan | 0.6407 |
pearson_euclidean | 0.6205 |
spearman_euclidean | 0.6394 |
pearson_dot | 0.48 |
spearman_dot | 0.494 |
pearson_max | 0.6233 |
spearman_max | 0.6439 |
Semantic Similarity
- Dataset:
sts-test
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.5517 |
spearman_cosine | 0.5841 |
pearson_manhattan | 0.5842 |
spearman_manhattan | 0.5887 |
pearson_euclidean | 0.5824 |
spearman_euclidean | 0.587 |
pearson_dot | 0.4055 |
spearman_dot | 0.4048 |
pearson_max | 0.5842 |
spearman_max | 0.5887 |
Training Details
Training Dataset
sentence-transformers/all-nli
- Dataset: sentence-transformers/all-nli at cc6c526
- Size: 10,000 training samples
- Columns:
premise
,hypothesis
, andlabel
- Approximate statistics based on the first 1000 samples:
premise hypothesis label type string string int details - min: 6 tokens
- mean: 17.38 tokens
- max: 52 tokens
- min: 4 tokens
- mean: 10.7 tokens
- max: 31 tokens
- 0: ~33.40%
- 1: ~33.30%
- 2: ~33.30%
- Samples:
premise hypothesis label A person on a horse jumps over a broken down airplane.
A person is training his horse for a competition.
1
A person on a horse jumps over a broken down airplane.
A person is at a diner, ordering an omelette.
2
A person on a horse jumps over a broken down airplane.
A person is outdoors, on a horse.
0
- Loss:
SoftmaxLoss
Evaluation Dataset
sentence-transformers/all-nli
- Dataset: sentence-transformers/all-nli at cc6c526
- Size: 1,000 evaluation samples
- Columns:
premise
,hypothesis
, andlabel
- Approximate statistics based on the first 1000 samples:
premise hypothesis label type string string int details - min: 6 tokens
- mean: 18.44 tokens
- max: 57 tokens
- min: 5 tokens
- mean: 10.57 tokens
- max: 25 tokens
- 0: ~33.10%
- 1: ~33.30%
- 2: ~33.60%
- Samples:
premise hypothesis label Two women are embracing while holding to go packages.
The sisters are hugging goodbye while holding to go packages after just eating lunch.
1
Two women are embracing while holding to go packages.
Two woman are holding packages.
0
Two women are embracing while holding to go packages.
The men are fighting outside a deli.
2
- Loss:
SoftmaxLoss
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 16per_device_eval_batch_size
: 16num_train_epochs
: 1warmup_ratio
: 0.1bf16
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Falseper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 1max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Truefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Nonedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
---|---|---|---|---|---|
0 | 0 | - | - | 0.5931 | - |
0.16 | 100 | 1.056 | 0.9278 | 0.6555 | - |
0.32 | 200 | 0.8966 | 0.8751 | 0.6381 | - |
0.48 | 300 | 0.8646 | 0.8393 | 0.6170 | - |
0.64 | 400 | 0.8328 | 0.8100 | 0.5804 | - |
0.8 | 500 | 0.8307 | 0.7940 | 0.6413 | - |
0.96 | 600 | 0.8373 | 0.7602 | 0.6439 | - |
1.0 | 625 | - | - | - | 0.5841 |
Environmental Impact
Carbon emissions were measured using CodeCarbon.
- Energy Consumed: 0.009 kWh
- Carbon Emitted: 0.003 kg of CO2
- Hours Used: 0.049 hours
Training Hardware
- On Cloud: No
- GPU Model: 1 x NVIDIA GeForce RTX 3090
- CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
- RAM Size: 31.78 GB
Framework Versions
- Python: 3.11.6
- Sentence Transformers: 3.0.0.dev0
- Transformers: 4.41.0.dev0
- PyTorch: 2.3.0+cu121
- Accelerate: 0.26.1
- Datasets: 2.18.0
- Tokenizers: 0.19.1
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",
}