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-b16")
# 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, 0.4274, 0.2306],
#         [0.4274, 1.0000, 0.3276],
#         [0.2306, 0.3276, 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	0.8448	0.7969
spearman_cosine	0.8425	0.7943

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	0.8443	0.7963
spearman_cosine	0.8424	0.7951

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	0.8399	0.7917
spearman_cosine	0.8394	0.7937

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	0.8186	0.7759
spearman_cosine	0.8249	0.783

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	0.3108	0.3026
spearman_cosine	0.438	0.3979

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: 16
per_device_eval_batch_size: 16
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: 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
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
0.0399	500	9.7558	5.4971	0.8366	0.8394	0.8364	0.8116	0.3516	-	-	-	-	-
0.0799	1000	5.8126	5.3466	0.8265	0.8262	0.8221	0.7994	0.3604	-	-	-	-	-
0.1198	1500	5.6179	5.3155	0.8365	0.8342	0.8297	0.8074	0.3820	-	-	-	-	-
0.1598	2000	5.4337	5.0697	0.8392	0.8383	0.8347	0.8125	0.4098	-	-	-	-	-
0.1997	2500	5.2708	5.1591	0.8320	0.8296	0.8259	0.8051	0.3725	-	-	-	-	-
0.2397	3000	5.2173	5.1042	0.8300	0.8291	0.8255	0.8044	0.3829	-	-	-	-	-
0.2796	3500	5.0789	4.9034	0.8299	0.8277	0.8231	0.7996	0.3710	-	-	-	-	-
0.3196	4000	5.1056	4.7930	0.8419	0.8415	0.8372	0.8162	0.4059	-	-	-	-	-
0.3595	4500	4.9763	4.8291	0.8422	0.8406	0.8355	0.8159	0.3812	-	-	-	-	-
0.3995	5000	4.9729	4.9692	0.8452	0.8435	0.8405	0.8238	0.4114	-	-	-	-	-
0.4394	5500	4.7542	4.9973	0.8394	0.8387	0.8357	0.8190	0.3756	-	-	-	-	-
0.4793	6000	4.7886	4.7710	0.8475	0.8475	0.8453	0.8285	0.4099	-	-	-	-	-
0.5193	6500	4.7406	4.6588	0.8417	0.8415	0.8385	0.8232	0.4347	-	-	-	-	-
0.5592	7000	4.7258	4.7451	0.8465	0.8460	0.8436	0.8249	0.4287	-	-	-	-	-
0.5992	7500	4.5991	4.7196	0.8396	0.8386	0.8357	0.8207	0.4000	-	-	-	-	-
0.6391	8000	4.5976	4.6225	0.8416	0.8409	0.8369	0.8183	0.4153	-	-	-	-	-
0.6791	8500	4.5607	4.6760	0.8407	0.8412	0.8372	0.8208	0.4317	-	-	-	-	-
0.7190	9000	4.5406	4.6796	0.8399	0.8395	0.8359	0.8197	0.4321	-	-	-	-	-
0.7590	9500	4.5464	4.5882	0.8395	0.8395	0.8366	0.8205	0.4305	-	-	-	-	-
0.7989	10000	4.4328	4.5758	0.8427	0.8426	0.8400	0.8245	0.4210	-	-	-	-	-
0.8389	10500	4.495	4.5487	0.8402	0.8402	0.8367	0.8214	0.4146	-	-	-	-	-
0.8788	11000	4.392	4.5094	0.8420	0.8419	0.8390	0.8244	0.4408	-	-	-	-	-
0.9188	11500	4.4206	4.4939	0.8431	0.8437	0.8403	0.8266	0.4411	-	-	-	-	-
0.9587	12000	4.3311	4.4776	0.8415	0.8413	0.8384	0.8236	0.4378	-	-	-	-	-
0.9986	12500	4.3707	4.4892	0.8425	0.8424	0.8394	0.8249	0.4380	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	0.7943	0.7951	0.7937	0.7830	0.3979

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}
}

Downloads last month: 6

Safetensors

Model size

82.1M params

Tensor type

F32

Model tree for wilsonmarciliojr/matryoshka-embed-b16

Base model

distilbert/distilroberta-base

Finetuned

(723)

this model

Dataset used to train wilsonmarciliojr/matryoshka-embed-b16

Evaluation results

Pearson Cosine on sts dev 768
self-reported

0.845
Spearman Cosine on sts dev 768
self-reported

0.843
Pearson Cosine on sts dev 512
self-reported

0.844
Spearman Cosine on sts dev 512
self-reported

0.842
Pearson Cosine on sts dev 256
self-reported

0.840
Spearman Cosine on sts dev 256
self-reported

0.839
Pearson Cosine on sts dev 64
self-reported

0.819
Spearman Cosine on sts dev 64
self-reported

0.825
Pearson Cosine on sts dev 2
self-reported

0.311
Spearman Cosine on sts dev 2
self-reported

0.438