This is a sentence-transformers model finetuned from sentence-transformers/stsb-distilbert-base on the sentence-transformers/quora-duplicates 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: sentence-transformers/stsb-distilbert-base
Maximum Sequence Length: 128 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- sentence-transformers/quora-duplicates
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': 128, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/stsb-distilbert-base-mnrl")
# Run inference
sentences = [
    'Is Cicret a scam?',
    'Is the Cicret Bracelet a scam?',
    'Can you eat only once a day?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Binary Classification

Dataset: quora-duplicates
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.816
cosine_accuracy_threshold	0.7867
cosine_f1	0.7286
cosine_f1_threshold	0.7353
cosine_precision	0.6746
cosine_recall	0.7919
cosine_ap	0.7731
dot_accuracy	0.807
dot_accuracy_threshold	150.9795
dot_f1	0.7224
dot_f1_threshold	137.3444
dot_precision	0.6641
dot_recall	0.7919
dot_ap	0.7492
manhattan_accuracy	0.81
manhattan_accuracy_threshold	195.8866
manhattan_f1	0.7246
manhattan_f1_threshold	237.6859
manhattan_precision	0.6293
manhattan_recall	0.854
manhattan_ap	0.7611
euclidean_accuracy	0.81
euclidean_accuracy_threshold	8.7739
euclidean_f1	0.7261
euclidean_f1_threshold	10.8438
euclidean_precision	0.6281
euclidean_recall	0.8602
euclidean_ap	0.7612
max_accuracy	0.816
max_accuracy_threshold	195.8866
max_f1	0.7286
max_f1_threshold	237.6859
max_precision	0.6746
max_recall	0.8602
max_ap	0.7731

Paraphrase Mining

Dataset: quora-duplicates-dev
Evaluated with ParaphraseMiningEvaluator

Metric	Value
average_precision	0.5349
f1	0.5395
precision	0.5175
recall	0.5635
threshold	0.762

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9646
cosine_accuracy@3	0.9926
cosine_accuracy@5	0.9956
cosine_accuracy@10	0.9986
cosine_precision@1	0.9646
cosine_precision@3	0.4293
cosine_precision@5	0.2754
cosine_precision@10	0.1452
cosine_recall@1	0.8301
cosine_recall@3	0.9609
cosine_recall@5	0.9808
cosine_recall@10	0.9935
cosine_ndcg@10	0.9795
cosine_mrr@10	0.979
cosine_map@100	0.9718
dot_accuracy@1	0.9574
dot_accuracy@3	0.9876
dot_accuracy@5	0.9924
dot_accuracy@10	0.9978
dot_precision@1	0.9574
dot_precision@3	0.4257
dot_precision@5	0.2737
dot_precision@10	0.1447
dot_recall@1	0.8238
dot_recall@3	0.9538
dot_recall@5	0.9764
dot_recall@10	0.9918
dot_ndcg@10	0.9741
dot_mrr@10	0.9731
dot_map@100	0.9646

Training Details

Training Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 100,000 training samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 6 tokens
mean: 13.85 tokens
max: 42 tokens
min: 6 tokens
mean: 13.65 tokens
max: 44 tokens
min: 4 tokens
mean: 14.76 tokens
max: 64 tokens

Samples:

anchor	positive	negative
`Why in India do we not have one on one political debate as in USA?`	`Why cant we have a public debate between politicians in India like the one in US?`	`Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?`
`What is OnePlus One?`	`How is oneplus one?`	`Why is OnePlus One so good?`
`Does our mind control our emotions?`	`How do smart and successful people control their emotions?`	`How can I control my positive emotions for the people whom I love but they don't care about me?`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Evaluation Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 1,000 evaluation samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 7 tokens
mean: 13.84 tokens
max: 43 tokens
min: 6 tokens
mean: 13.8 tokens
max: 38 tokens
min: 6 tokens
mean: 14.71 tokens
max: 56 tokens

Samples:

anchor	positive	negative
`Which programming language is best for developing low-end games?`	`What coding language should I learn first for making games?`	`I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms?`
`Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump?`	`Should Meryl Streep be using her position to attack the president?`	`Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?`
`Where can I found excellent commercial fridges in Sydney?`	`Where can I found impressive range of commercial fridges in Sydney?`	`What is the best grocery delivery service in Sydney?`

Loss: MultipleNegativesRankingLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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: False
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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: 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
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: None
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_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	cosine_map@100	quora-duplicates-dev_average_precision	quora-duplicates_max_ap
0	0	-	-	0.9245	0.4200	0.6890
0.0640	100	0.2535	-	-	-	-
0.1280	200	0.1732	-	-	-	-
0.1599	250	-	0.1021	0.9601	0.5033	0.7342
0.1919	300	0.1465	-	-	-	-
0.2559	400	0.1186	-	-	-	-
0.3199	500	0.1159	0.0773	0.9653	0.5247	0.7453
0.3839	600	0.1088	-	-	-	-
0.4479	700	0.0993	-	-	-	-
0.4798	750	-	0.0665	0.9666	0.5264	0.7655
0.5118	800	0.0952	-	-	-	-
0.5758	900	0.0799	-	-	-	-
0.6398	1000	0.0855	0.0570	0.9709	0.5391	0.7717
0.7038	1100	0.0804	-	-	-	-
0.7678	1200	0.073	-	-	-	-
0.7997	1250	-	0.0513	0.9719	0.5329	0.7662
0.8317	1300	0.0741	-	-	-	-
0.8957	1400	0.0699	-	-	-	-
0.9597	1500	0.0755	0.0476	0.9718	0.5349	0.7731

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.039 kWh
Carbon Emitted: 0.015 kg of CO2
Hours Used: 0.169 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 3.0.0.dev0
Transformers: 4.41.0.dev0
PyTorch: 2.3.0+cu121
Accelerate: 0.26.1
Datasets: 2.18.0
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

MultipleNegativesRankingLoss

bibtex

@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}
}

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 13.85 tokens max: 42 tokens	min: 6 tokens mean: 13.65 tokens max: 44 tokens	min: 4 tokens mean: 14.76 tokens max: 64 tokens