metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10000
  - loss:SoftmaxLoss
base_model: google-bert/bert-base-uncased
datasets: []
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: >-
      A man selling donuts to a customer during a world exhibition event held in
      the city of Angeles
    sentences:
      - The man is doing tricks.
      - A woman drinks her coffee in a small cafe.
      - The building is made of logs.
  - source_sentence: A group of people prepare hot air balloons for takeoff.
    sentences:
      - There are hot air balloons on the ground and air.
      - A man is in an art museum.
      - People watch another person do a trick.
  - source_sentence: Three workers are trimming down trees.
    sentences:
      - The goalie is sleeping at home.
      - There are three workers
      - The girl has brown hair.
  - source_sentence: >-
      Two brown-haired men wearing short-sleeved shirts and shorts are climbing
      stairs.
    sentences:
      - The men have blonde hair.
      - A bicyclist passes an esthetically beautiful building on a sunny day
      - Two men are dancing.
  - source_sentence: A man is sitting in on the side of the street with brass pots.
    sentences:
      - a younger boy looks at his father
      - Children are at the beach.
      - a man does not have brass pots
pipeline_tag: sentence-similarity
co2_eq_emissions:
  emissions: 147.28843774992524
  energy_consumed: 0.2758298255748315
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD EPYC 7H12 64-Core Processor
  ram_total_size: 229.14864349365234
  hours_used: 0.351
  hardware_used: 8 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: 0.47725003430658275
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.5475746919034576
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.5043805022296893
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.5420702830995872
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.5083739540394052
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.544209699690841
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4458579859528435
            name: Pearson Dot
          - type: spearman_dot
            value: 0.4698642508787034
            name: Spearman Dot
          - type: pearson_max
            value: 0.5083739540394052
            name: Pearson Max
          - type: spearman_max
            value: 0.5475746919034576
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.5320947494943107
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.5317279446221387
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.5575308236485216
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.5554390408837996
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.55587770863865
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.5535804159700501
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.2787697886285483
            name: Pearson Dot
          - type: spearman_dot
            value: 0.2710358104528421
            name: Spearman Dot
          - type: pearson_max
            value: 0.5575308236485216
            name: Pearson Max
          - type: spearman_max
            value: 0.5554390408837996
            name: Spearman Max
          - type: pearson_cosine
            value: 0.4493844540252116
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.4694611677633312
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.4773641092320219
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.4763054309792941
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.4796801942910325
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.47774521406648734
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4081600817978359
            name: Pearson Dot
          - type: spearman_dot
            value: 0.3898881150281674
            name: Spearman Dot
          - type: pearson_max
            value: 0.4796801942910325
            name: Pearson Max
          - type: spearman_max
            value: 0.47774521406648734
            name: Spearman Max

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: 512 tokens
Output Dimensionality: 768 tokens
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': 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("jilangdi/bert-base-uncased-nli-v1")
# Run inference
sentences = [
    'A man is sitting in on the side of the street with brass pots.',
    'a man does not have brass pots',
    'Children are at the beach.',
]
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

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4773
spearman_cosine	0.5476
pearson_manhattan	0.5044
spearman_manhattan	0.5421
pearson_euclidean	0.5084
spearman_euclidean	0.5442
pearson_dot	0.4459
spearman_dot	0.4699
pearson_max	0.5084
spearman_max	0.5476

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.5321
spearman_cosine	0.5317
pearson_manhattan	0.5575
spearman_manhattan	0.5554
pearson_euclidean	0.5559
spearman_euclidean	0.5536
pearson_dot	0.2788
spearman_dot	0.271
pearson_max	0.5575
spearman_max	0.5554

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4494
spearman_cosine	0.4695
pearson_manhattan	0.4774
spearman_manhattan	0.4763
pearson_euclidean	0.4797
spearman_euclidean	0.4777
pearson_dot	0.4082
spearman_dot	0.3899
pearson_max	0.4797
spearman_max	0.4777

Training Details

Training Dataset

Unnamed Dataset

Size: 10,000 training samples
Columns: premise, hypothesis, and label
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%

	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

Unnamed Dataset

Size: 1,000 evaluation samples
Columns: premise, hypothesis, and label
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%

	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: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 5
warmup_ratio: 0.1
fp16: True

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
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: 5
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: 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}
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
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	0	-	-	0.5931	-
1.0	79	-	-	-	0.5317
1.2658	100	0.545	0.9351	0.5973	-
2.5316	200	0.5286	0.9535	0.5660	-
3.7975	300	0.3553	1.0364	0.5476	-
5.0	395	-	-	-	0.4695

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.276 kWh
Carbon Emitted: 0.147 kg of CO2
Hours Used: 0.351 hours

Training Hardware

On Cloud: No
GPU Model: 8 x NVIDIA GeForce RTX 3090
CPU Model: AMD EPYC 7H12 64-Core Processor
RAM Size: 229.15 GB

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.3.1+cu121
Accelerate: 0.31.0
Datasets: 2.19.2
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",
}