metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-mpnet-base-v2
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 boy is vacuuming.
    sentences:
      - A little boy is vacuuming the floor.
      - A woman is riding an elephant.
      - People are sitting on benches.
  - source_sentence: A man shoots a man.
    sentences:
      - The man is aiming a gun.
      - A man is tracking in the wood.
      - A woman leading a white horse.
  - source_sentence: A plane in the sky.
    sentences:
      - A plane rides on a road.
      - A tiger walks around aimlessly.
      - Two dogs playing on the shore.
  - source_sentence: A baby is laughing.
    sentences:
      - The baby laughed in his car seat.
      - A toddler walks down a hallway.
      - There are dogs in the forest.
  - source_sentence: The gate is yellow.
    sentences:
      - The gate is blue.
      - US spends $50m on carp invasion
      - Suicide bomber strikes in Syria
pipeline_tag: sentence-similarity
co2_eq_emissions:
  emissions: 9.73131270828096
  energy_consumed: 0.025035406836808046
  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: 0.122
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.9105652572605438
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9097842782963139
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8999692728646553
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.909018931820409
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9003677259034385
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.9097842782963139
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.9105652590717077
            name: Pearson Dot
          - type: spearman_dot
            value: 0.9097842782963139
            name: Spearman Dot
          - type: pearson_max
            value: 0.9105652590717077
            name: Pearson Max
          - type: spearman_max
            value: 0.9097842782963139
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.8764756843077764
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8733461504859822
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8668031220817161
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8725075805222068
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8674774784108314
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8733464312456004
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8764756858675475
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8733464312456004
            name: Spearman Dot
          - type: pearson_max
            value: 0.8764756858675475
            name: Pearson Max
          - type: spearman_max
            value: 0.8733464312456004
            name: Spearman Max

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the sentence-transformers/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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- sentence-transformers/stsb
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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (2): Normalize()
)

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/all-mpnet-base-v2-sts")
# Run inference
sentences = [
    'The gate is yellow.',
    'The gate is blue.',
    'US spends $50m on carp invasion',
]
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	0.9106
spearman_cosine	0.9098
pearson_manhattan	0.9
spearman_manhattan	0.909
pearson_euclidean	0.9004
spearman_euclidean	0.9098
pearson_dot	0.9106
spearman_dot	0.9098
pearson_max	0.9106
spearman_max	0.9098

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8765
spearman_cosine	0.8733
pearson_manhattan	0.8668
spearman_manhattan	0.8725
pearson_euclidean	0.8675
spearman_euclidean	0.8733
pearson_dot	0.8765
spearman_dot	0.8733
pearson_max	0.8765
spearman_max	0.8733

Training Details

Training Dataset

sentence-transformers/stsb

Dataset: sentence-transformers/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

	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

sentence-transformers/stsb

Dataset: sentence-transformers/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

	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
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: False
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: 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
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: None
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_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	0.0218	0.0210	0.8939	-
0.5556	200	0.0203	0.0190	0.8990	-
0.8333	300	0.019	0.0183	0.9021	-
1.1111	400	0.0147	0.0190	0.9033	-
1.3889	500	0.0092	0.0187	0.9038	-
1.6667	600	0.0089	0.0180	0.9031	-
1.9444	700	0.0089	0.0184	0.9045	-
2.2222	800	0.0056	0.0181	0.9066	-
2.5	900	0.0045	0.0182	0.9075	-
2.7778	1000	0.0047	0.0179	0.9083	-
3.0556	1100	0.0045	0.0179	0.9090	-
3.3333	1200	0.003	0.0176	0.9088	-
3.6111	1300	0.0029	0.0176	0.9093	-
3.8889	1400	0.0031	0.0176	0.9098	-
4.0	1440	-	-	-	0.8733

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.025 kWh
Carbon Emitted: 0.010 kg of CO2
Hours Used: 0.122 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

@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",
}