metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:3204256
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: distilbert/distilroberta-base
widget:
  - source_sentence: >-
      Two young boys of opposing teams play football, while wearing full
      protection uniforms and helmets.
    sentences:
      - 2 young boys compete in martial arts.
      - Men playing football.
      - Some people are playing sports.
      - There are at least 2 players.
      - The football players are on a field
      - A football playing chasing the opposing teams player in a game.
  - source_sentence: >-
      An Indian woman is washing and cleaning dirty laundry at a lake and in the
      background is a kid who appears to have jumped into the lake.
    sentences:
      - The girl has swam before.
      - A woman gets out of the pool.
      - >-
        A young child is jumping into the arms of a woman wearing a black
        swimming suit while in a pool.
      - A person is near a body of water.
      - The baby is wet.
      - >-
        The mother is responsible for the raising of the native islander
        children.
  - source_sentence: A little boy in a blue shirt holding a toy.
    sentences:
      - A small boy is in a pool.
      - The child is indoors .
      - A boy is holding a rope.
      - >-
        A toddler in a blue one-piece plays with a stack of plastic tubs, while
        toys are scattered on the floor behind him.
      - Toddlers are in the room with toys.
      - >-
        a kid is playing with a green, white and red spinning toy that turning
        on the ground.
  - source_sentence: >-
      A lot of people walking outside a row of shops with an older man with his
      hands in his pocket is closer to the camera.
    sentences:
      - There are people facing away from the camera.
      - people walking to a special place.
      - People shop at a clothing sale.
      - A vendor is outside with other people.
      - The older men are visiting with each other.
      - A group of people walks past some trees and brown buildings.
  - source_sentence: A baby at the end of a slip and slide at a party
    sentences:
      - An adult and a kid are engaged in an activity.
      - A man is playing with a baby on a deck.
      - A baby in a bib is making funny faces at the camera.
      - A toddler is playing outside.
      - There is more than one child.
      - One person faces another person who's holding a baby.
datasets:
  - wilsonmarciliojr/all-nli-knn-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 dev 768
          type: sts-dev-768
        metrics:
          - type: pearson_cosine
            value: 0.7936668588977441
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7848882989972251
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 512
          type: sts-dev-512
        metrics:
          - type: pearson_cosine
            value: 0.7937657981749313
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7856118515167717
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 256
          type: sts-dev-256
        metrics:
          - type: pearson_cosine
            value: 0.790895109048575
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7838022433432926
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 64
          type: sts-dev-64
        metrics:
          - type: pearson_cosine
            value: 0.7799703808618819
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7780979093232232
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 2
          type: sts-dev-2
        metrics:
          - type: pearson_cosine
            value: 0.2274909708889573
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.3272510104227767
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.7533772097431138
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7348404906981064
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.7538280187021393
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7354710781946179
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.75226937168666
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7353798135632856
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.7396292871029544
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.727399503720101
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 2
          type: sts-test-2
        metrics:
          - type: pearson_cosine
            value: 0.21579396507487203
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.3229925164682956
            name: Spearman Cosine

SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base on the all-nli-knn-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-knn-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-knn")
# Run inference
sentences = [
    'A baby at the end of a slip and slide at a party',
    'A man is playing with a baby on a deck.',
    'A baby in a bib is making funny faces at the camera.',
]
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, 0.4520, 0.5252],
#         [0.4520, 1.0000, 0.2916],
#         [0.5252, 0.2916, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Datasets: sts-dev-768 and sts-test-768
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 768
}
```

Metric	sts-dev-768	sts-test-768
pearson_cosine	0.7937	0.7534
spearman_cosine	0.7849	0.7348

Semantic Similarity

Datasets: sts-dev-512 and sts-test-512
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 512
}
```

Metric	sts-dev-512	sts-test-512
pearson_cosine	0.7938	0.7538
spearman_cosine	0.7856	0.7355

Semantic Similarity

Datasets: sts-dev-256 and sts-test-256
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	sts-dev-256	sts-test-256
pearson_cosine	0.7909	0.7523
spearman_cosine	0.7838	0.7354

Semantic Similarity

Datasets: sts-dev-64 and sts-test-64
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	sts-dev-64	sts-test-64
pearson_cosine	0.78	0.7396
spearman_cosine	0.7781	0.7274

Semantic Similarity

Datasets: sts-dev-2 and sts-test-2
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 2
}
```

Metric	sts-dev-2	sts-test-2
pearson_cosine	0.2275	0.2158
spearman_cosine	0.3273	0.323

Training Details

Training Dataset

all-nli-knn-hard-negatives

Dataset: all-nli-knn-hard-negatives at c7814a7
Size: 3,204,256 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: 8 tokens mean: 16.58 tokens max: 50 tokens	min: 6 tokens mean: 14.56 tokens max: 59 tokens	min: 5 tokens mean: 9.62 tokens max: 16 tokens	min: 5 tokens mean: 9.24 tokens max: 16 tokens	min: 5 tokens mean: 9.16 tokens max: 18 tokens	min: 6 tokens mean: 9.43 tokens max: 17 tokens	min: 5 tokens mean: 9.41 tokens max: 18 tokens

Samples:

anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
`An older man is drinking orange juice at a restaurant.`	`An elderly man is drinking orange juice at a cafe.`	`An elderly gentleman eats.`	`A man has many oranges in his baskets.`	`An elderly person is being served food`	`A man works at a restaurant`	`There is a older man.`
`An older man is drinking orange juice at a restaurant.`	`A man drinking orange juice while walking.`	`An elderly gentleman eats.`	`A man has many oranges in his baskets.`	`An elderly person is being served food`	`A man works at a restaurant`	`There is a older man.`
`An older man is drinking orange juice at a restaurant.`	`A man drinks orange juice and walks outside.`	`An elderly gentleman eats.`	`A man has many oranges in his baskets.`	`An elderly person is being served food`	`A man works at a restaurant`	`There is a older man.`

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-knn-hard-negatives

Dataset: all-nli-knn-hard-negatives at c7814a7
Size: 103,904 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: 9 tokens mean: 17.34 tokens max: 36 tokens	min: 6 tokens mean: 17.12 tokens max: 52 tokens	min: 5 tokens mean: 9.27 tokens max: 21 tokens	min: 6 tokens mean: 9.98 tokens max: 21 tokens	min: 5 tokens mean: 9.35 tokens max: 21 tokens	min: 5 tokens mean: 9.12 tokens max: 16 tokens	min: 6 tokens mean: 9.47 tokens max: 23 tokens

Samples:

anchor	positive	negative_1	negative_2	negative_3	negative_4	negative_5
`Two women are embracing while holding to go packages.`	`Two women in a embrace of greetings, one of them is holding flowers and they are greeting each other of a kiss.`	`Two women are in the city.`	`The women each have one head.`	`Two women are drinking wine and having a conversation.`	`women carry food on plates`	`Two people are kissing each other.`
`Two women are embracing while holding to go packages.`	`Two women wearing boots and holding bags are talking to each other.`	`Two women are in the city.`	`The women each have one head.`	`Two women are drinking wine and having a conversation.`	`women carry food on plates`	`Two people are kissing each other.`
`Two women are embracing while holding to go packages.`	`Two women are wet while holding hands with a long building and buses in the background.`	`Two women are in the city.`	`The women each have one head.`	`Two women are drinking wine and having a conversation.`	`women carry food on plates`	`Two people are kissing each other.`

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: 324
per_device_eval_batch_size: 324
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: 324
per_device_eval_batch_size: 324
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	Training Loss	Validation Loss	sts-dev-768_spearman_cosine	sts-dev-512_spearman_cosine	sts-dev-256_spearman_cosine	sts-dev-64_spearman_cosine	sts-dev-2_spearman_cosine	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
0.1011	1000	15.5729	11.0151	0.8103	0.8099	0.8066	0.7934	0.3373	-	-	-	-	-
0.2022	2000	11.3861	10.5141	0.8084	0.8084	0.8063	0.7939	0.3636	-	-	-	-	-
0.3033	3000	10.5075	10.5011	0.8061	0.8068	0.8051	0.7960	0.3659	-	-	-	-	-
0.4044	4000	9.9884	10.7506	0.7900	0.7906	0.7875	0.7770	0.3387	-	-	-	-	-
0.5056	5000	9.5581	10.7602	0.7997	0.7997	0.7974	0.7882	0.3496	-	-	-	-	-
0.6067	6000	9.2037	10.6260	0.7930	0.7930	0.7910	0.7846	0.3549	-	-	-	-	-
0.7078	7000	8.9519	10.5886	0.7910	0.7921	0.7903	0.7840	0.3342	-	-	-	-	-
0.8089	8000	8.7682	10.6864	0.7896	0.7903	0.7881	0.7819	0.3311	-	-	-	-	-
0.9100	9000	8.6166	10.6835	0.7849	0.7856	0.7838	0.7781	0.3273	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	0.7348	0.7355	0.7354	0.7274	0.3230

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}
}