metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:200266
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: distilbert/distilroberta-base
widget:
  - source_sentence: >-
      A couple is a standing together the woman is adjusting a flower on the
      man's lapel and they are dressed in wedding apparel.
    sentences:
      - the two people were together
      - The men and women are dressed in clothes for the beach.
      - A couple is outside with their dog.
      - There are several people standing.
      - People are going to a wedding.
      - A couple of people stand on stage.
  - source_sentence: >-
      A man wearing a blue hat and a blue shirt selling bananas from his wheel
      cart on the street.
    sentences:
      - A vendor selling bananas.
      - A vendor is outside with other people.
      - A man peels fruit.
      - The man is on a sidewalk.
      - A fruit market is selling vegetables
      - A man in a store.
  - source_sentence: >-
      A woman with a bright red umbrella is jumping high in the air, she has on
      a knit hat and black shirt and colorful boots.
    sentences:
      - A woman in black is jumping in the air with a red umbrella.
      - A woman outside.
      - The woman is not standing up.
      - woman stands on ladder
      - There is a woman wearing purple outside.
      - A woman is sitting outside.
  - source_sentence: A man is taking pictures hanging outside of a red rally car.
    sentences:
      - The man is near the car.
      - people take pictures
      - A man outside.
      - The man is outdoors.
      - A man painting outside.
      - A vehicle travels outdoors.
  - source_sentence: A man reading the paper at a cafe.
    sentences:
      - A man starring at a piece of paper.
      - The man is outside.
      - A man is sitting.
      - The man is cooking.
      - There is a man outside.
      - Someone likes to get comments from readers of a paper.
datasets:
  - wilsonmarciliojr/all-nli-hard-negatives
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on distilbert/distilroberta-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.8117445187439676
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8045789908263759
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.8103553493552982
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8040272614140894
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.8071235860511184
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8041325315160667
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.790701064948115
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7932433651370305
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 2
          type: sts-test-2
        metrics:
          - type: pearson_cosine
            value: 0.3114131647840022
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.42302032029735914
            name: Spearman Cosine

SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base on the all-nli-hard-negatives 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/distilroberta-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- all-nli-hard-negatives

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, 'architecture': 'RobertaModel'})
  (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("wilsonmarciliojr/matryoshka-embed-b512")
# Run inference
sentences = [
    'A man reading the paper at a cafe.',
    'A man starring at a piece of paper.',
    'A man is sitting.',
]
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, 0.4452, 0.2729],
#         [0.4452, 1.0000, 0.2601],
#         [0.2729, 0.2601, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 768
}
```

Metric	Value
pearson_cosine	0.8117
spearman_cosine	0.8046

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 512
}
```

Metric	Value
pearson_cosine	0.8104
spearman_cosine	0.804

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	Value
pearson_cosine	0.8071
spearman_cosine	0.8041

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	Value
pearson_cosine	0.7907
spearman_cosine	0.7932

Semantic Similarity

Dataset: sts-test-2
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 2
}
```

Metric	Value
pearson_cosine	0.3114
spearman_cosine	0.423

Training Details

Training Dataset

all-nli-hard-negatives

Dataset: all-nli-hard-negatives at 9e4fbfd
Size: 200,266 training samples
Columns: anchor, positive, negative_1, negative_2, negative_3, negative_4, and negative_5

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
type	string	string	string	string	string	string	string
details	min: 7 tokens mean: 15.96 tokens max: 50 tokens	min: 4 tokens mean: 10.29 tokens max: 22 tokens	min: 4 tokens mean: 9.31 tokens max: 24 tokens	min: 4 tokens mean: 9.21 tokens max: 24 tokens	min: 4 tokens mean: 9.16 tokens max: 24 tokens	min: 4 tokens mean: 9.14 tokens max: 22 tokens	min: 4 tokens mean: 9.34 tokens max: 27 tokens

Samples:

anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
`An older man is drinking orange juice at a restaurant.`	`A man is drinking juice.`	`A man seated at a restaurant.`	`The older man is making food.`	`the guy in the orange shirt has food in front of him`	`An elderly person is being served food`	`A man wears an orange shirt.`
`A man with blond-hair, and a brown shirt drinking out of a public water fountain.`	`A blond man drinking water from a fountain.`	`Man having a drink.`	`A man is playing in the fountain.`	`A man is drinking something.`	`The water fountain is wet.`	`This man is wet`
`Two women, holding food carryout containers, hug.`	`Two women hug each other.`	`The two woman are holding their arms`	`Both women have things in their hands.`	`Two woman standing near each other while one of them holds an item.`	`Two women carry bags`	`Two people give each other a hug.`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        64,
        2
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

all-nli-hard-negatives

Dataset: all-nli-hard-negatives at 9e4fbfd
Size: 6,494 evaluation samples
Columns: anchor, positive, negative_1, negative_2, negative_3, negative_4, and negative_5

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
type	string	string	string	string	string	string	string
details	min: 6 tokens mean: 17.84 tokens max: 66 tokens	min: 4 tokens mean: 9.91 tokens max: 29 tokens	min: 4 tokens mean: 9.22 tokens max: 27 tokens	min: 5 tokens mean: 9.38 tokens max: 25 tokens	min: 4 tokens mean: 9.28 tokens max: 29 tokens	min: 4 tokens mean: 9.35 tokens max: 41 tokens	min: 4 tokens mean: 9.54 tokens max: 41 tokens

Samples:

anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
`Two women are embracing while holding to go packages.`	`Two woman are holding packages.`	`A group of women with flowers.`	`There are women relaxing.`	`Women are holding a flag`	`A woman is holding one young children with another standing next to her`	`An old woman is carrying two pails.`
`Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.`	`Two kids in numbered jerseys wash their hands.`	`Children are walking.`	`THe children are playing.`	`Two kids are playing outside.`	`The people have clothes on.`	`Children are playing a game`
`A man selling donuts to a customer during a world exhibition event held in the city of Angeles`	`A man selling donuts to a customer.`	`A man is giving a presentation.`	`Goods and Services are sold by undercover agents..`	`It is called Service Merchandise here.`	`A street vendor is outside.`	`I'm happy that I don't work in a store.`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        64,
        2
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
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: 1.0
num_train_epochs: 1
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: 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: False
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: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	sts-test-768_spearman_cosine	sts-test-512_spearman_cosine	sts-test-256_spearman_cosine	sts-test-64_spearman_cosine	sts-test-2_spearman_cosine
-1	-1	0.8046	0.8040	0.8041	0.7932	0.4230

Framework Versions

Python: 3.10.12
Sentence Transformers: 5.0.0
Transformers: 4.53.1
PyTorch: 2.7.1+cu126
Accelerate: 1.8.1
Datasets: 3.6.0
Tokenizers: 0.21.2

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}