SentenceTransformer based on distilbert/distilbert-base-uncased

This is a sentence-transformers model finetuned from distilbert/distilbert-base-uncased on the 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 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- 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, 'architecture': '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("m-kojima/distilbert-base-uncased-sts-matryoshka")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man sitting on the floor in a room is strumming a guitar.',
]
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, 0.7339, 0.3618],
#         [0.7339, 1.0000, 0.3923],
#         [0.3618, 0.3923, 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	0.8634	0.8354
spearman_cosine	0.8769	0.854

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	0.8615	0.8343
spearman_cosine	0.8765	0.8537

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	0.8579	0.8253
spearman_cosine	0.8739	0.8487

Semantic Similarity

Datasets: sts-dev-128 and sts-test-128
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
```
{
    "truncate_dim": 128
}
```

Metric	sts-dev-128	sts-test-128
pearson_cosine	0.8482	0.8164
spearman_cosine	0.8701	0.8445

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	0.8313	0.8008
spearman_cosine	0.8606	0.8375

Training Details

Training Dataset

stsb

Dataset: 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: 0.45
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: 0.45 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: MatryoshkaLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

stsb

Dataset: 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: 0.42
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: 0.42 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: MatryoshkaLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "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: 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: 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: 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: 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: batch_sampler
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-128_spearman_cosine	sts-dev-64_spearman_cosine	sts-test-768_spearman_cosine	sts-test-512_spearman_cosine	sts-test-256_spearman_cosine	sts-test-128_spearman_cosine	sts-test-64_spearman_cosine
0.2778	100	22.9607	21.5053	0.8399	0.8390	0.8391	0.8345	0.8198	-	-	-	-	-
0.5556	200	21.7567	21.7006	0.8416	0.8410	0.8339	0.8291	0.8166	-	-	-	-	-
0.8333	300	21.6856	22.0550	0.8641	0.8630	0.8586	0.8544	0.8394	-	-	-	-	-
1.1111	400	21.1235	21.8466	0.8616	0.8609	0.8566	0.8528	0.8382	-	-	-	-	-
1.3889	500	20.3754	21.8009	0.8661	0.8659	0.8629	0.8582	0.8485	-	-	-	-	-
1.6667	600	20.2841	22.3990	0.8734	0.8726	0.8698	0.8644	0.8538	-	-	-	-	-
1.9444	700	20.6808	21.7617	0.8665	0.8664	0.8634	0.8589	0.8488	-	-	-	-	-
2.2222	800	19.4382	23.4419	0.8727	0.8724	0.8695	0.8647	0.8551	-	-	-	-	-
2.5	900	19.1241	23.1544	0.8720	0.8720	0.8682	0.8642	0.8513	-	-	-	-	-
2.7778	1000	19.3831	23.9067	0.8741	0.8739	0.8711	0.8662	0.8577	-	-	-	-	-
3.0556	1100	18.9196	24.3653	0.8766	0.8766	0.8738	0.8696	0.8603	-	-	-	-	-
3.3333	1200	18.0825	25.1969	0.8758	0.8760	0.8730	0.8690	0.8598	-	-	-	-	-
3.6111	1300	18.0855	25.9958	0.8755	0.8752	0.8723	0.8685	0.8590	-	-	-	-	-
3.8889	1400	18.3427	25.5680	0.8769	0.8765	0.8739	0.8701	0.8606	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	0.8540	0.8537	0.8487	0.8445	0.8375

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.1.1
Transformers: 4.53.0
PyTorch: 2.9.0+cu128
Accelerate: 1.10.1
Datasets: 3.6.0
Tokenizers: 0.21.4

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}
}

CoSENTLoss

@article{10531646,
    author={Huang, Xiang and Peng, Hao and Zou, Dongcheng and Liu, Zhiwei and Li, Jianxin and Liu, Kay and Wu, Jia and Su, Jianlin and Yu, Philip S.},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    title={CoSENT: Consistent Sentence Embedding via Similarity Ranking},
    year={2024},
    doi={10.1109/TASLP.2024.3402087}
}

Downloads last month: 10

Safetensors

Model size

66.4M params

Tensor type

F32

Model tree for m-kojima/distilbert-base-uncased-sts-matryoshka

Base model

distilbert/distilbert-base-uncased

Finetuned

(10536)

this model

Dataset used to train m-kojima/distilbert-base-uncased-sts-matryoshka

Evaluation results

Pearson Cosine on sts dev 768
self-reported

0.863
Spearman Cosine on sts dev 768
self-reported

0.877
Pearson Cosine on sts dev 512
self-reported

0.861
Spearman Cosine on sts dev 512
self-reported

0.877
Pearson Cosine on sts dev 256
self-reported

0.858
Spearman Cosine on sts dev 256
self-reported

0.874
Pearson Cosine on sts dev 128
self-reported

0.848
Spearman Cosine on sts dev 128
self-reported

0.870
Pearson Cosine on sts dev 64
self-reported

0.831
Spearman Cosine on sts dev 64
self-reported

0.861