metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:1K<n<10K
  - loss:CosineSimilarityLoss
base_model: distilbert/distilbert-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: A man shoots a man.
    sentences:
      - The target was being shot with bullets.
      - Two women compete in a contest.
      - Kittens are eating from dishes.
  - source_sentence: A man is spitting.
    sentences:
      - A man is crying.
      - The cougar is chasing the bear.
      - A slow loris hanging on a cord.
  - source_sentence: A man jumping rope
    sentences:
      - The man without a shirt is jumping.
      - Suicide bomber strikes in Syria
      - Two women sitting in lawn chairs.
  - source_sentence: A woman is reading.
    sentences:
      - The woman is pencilling on eye shadow.
      - Bombings kill 19 people in Iraq
      - A man with his dog on the beach.
  - source_sentence: A cat is on a robot.
    sentences:
      - A cat is pouncing on a trampoline.
      - Two men are standing in a room.
      - The two men are wearing jeans.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on distilbert/distilbert-base-uncased
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.8697331501677178
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8685180246535534
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8437823469562609
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8453821992823211
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8437006142247849
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8452387041309848
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8131236162716029
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8170086888260258
            name: Spearman Dot
          - type: pearson_max
            value: 0.8697331501677178
            name: Pearson Max
          - type: spearman_max
            value: 0.8685180246535534
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.8385072210953088
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8381420978910276
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8314551294633353
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8311067092857745
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8321704746684249
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.831638857612135
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7504803996099798
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7471600293342772
            name: Spearman Dot
          - type: pearson_max
            value: 0.8385072210953088
            name: Pearson Max
          - type: spearman_max
            value: 0.8381420978910276
            name: Spearman Max

SentenceTransformer based on distilbert/distilbert-base-uncased

This is a sentence-transformers model finetuned from distilbert/distilbert-base-uncased 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: distilbert/distilbert-base-uncased
Maximum Sequence Length: 512 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': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (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("pierreinalco/distilbert-base-uncased-sts")
# Run inference
sentences = [
    'A cat is on a robot.',
    'A cat is pouncing on a trampoline.',
    'Two men are standing in a room.',
]
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	0.8697
spearman_cosine	0.8685
pearson_manhattan	0.8438
spearman_manhattan	0.8454
pearson_euclidean	0.8437
spearman_euclidean	0.8452
pearson_dot	0.8131
spearman_dot	0.817
pearson_max	0.8697
spearman_max	0.8685

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8385
spearman_cosine	0.8381
pearson_manhattan	0.8315
spearman_manhattan	0.8311
pearson_euclidean	0.8322
spearman_euclidean	0.8316
pearson_dot	0.7505
spearman_dot	0.7472
pearson_max	0.8385
spearman_max	0.8381

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

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: 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
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	0.0836	0.0399	0.8029	-
0.5556	200	0.0334	0.0301	0.8481	-
0.8333	300	0.0282	0.0262	0.8578	-
1.1111	400	0.0204	0.0273	0.8593	-
1.3889	500	0.0138	0.0281	0.8589	-
1.6667	600	0.0118	0.0276	0.8566	-
1.9444	700	0.0128	0.0263	0.8614	-
2.2222	800	0.0077	0.0259	0.8685	-
2.5	900	0.0057	0.0254	0.8661	-
2.7778	1000	0.0059	0.0261	0.8677	-
3.0556	1100	0.0054	0.0258	0.8682	-
3.3333	1200	0.0039	0.0261	0.8668	-
3.6111	1300	0.0039	0.0261	0.8678	-
3.8889	1400	0.0037	0.0259	0.8685	-
4.0	1440	-	-	-	0.8381

Framework Versions

Python: 3.11.9
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0
Accelerate: 0.30.1
Datasets: 2.19.1
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",
}