This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (2): Normalize()
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    "Our Mission is to lower your overall insurance cost, and to provide one stop service for your insurance protection. We also strive to provide professional, personalized, and efficient service to each and every client. We've been insuring families and businesses in Laredo, McAllen, Edinburg, Mission and surrounding areas in Texas since 1988 and we're looking forward to working with you. ",
    'We are in need of a comprehensive insurance plan to safeguard our business and assets.',
    'We need a reliable car dealership to offer our clients top-quality vehicles.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9372
spearman_cosine	0.8723

Training Details

Training Dataset

Unnamed Dataset

Size: 371 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 371 samples:
sentence_0 sentence_1 label
type string string float
details
min: 25 tokens
mean: 98.46 tokens
max: 256 tokens
min: 12 tokens
mean: 15.73 tokens
max: 20 tokens
min: 0.6
mean: 0.71
max: 0.9

Samples:

sentence_0	sentence_1	label
Adderall is a prescription drug that contains the stimulants amphetamine and dextroamphetamine. It helps treat attention deficit hyperactivity disorder or ADHD and narcolepsy (a sleep disorder). You can buy Adderall online with a prescription. Adderall 30mg XR buy cheap product Adderall 30mg XR buy cheap online Adderall 30mg XR buy without prescription Adderall 30mg XR for sale online Adderall 30mg XR near me Buy Adderall 30mg online Buy Adderall 30mg XR online near me Buy cheap adderall 30Mg XR online Cheap Adderall 30Mg online How to buy adderall 30Mg online Order adderall 30Mg XR online Order Adderall 30 XR without prescription Adderall 30mg XR online Where to buy Adderall 30mg Online where to buy Adderall 30mg XR without prescription Anxietycare.online provides the best facilities to all our customers. We provide offers including rewards, discounts, and cash back with our products so that our customers can have better facilities and engage with us properly.	`We are looking for comprehensive automotive solutions to support our business needs.`	`0.8`
`Built on integrity and honesty, HighMark Roofing & Construction is bringing back trust in the local roofing and construction industry. You can trust that your project will be completed with professionalism and efficiently. Instead of just patching a problem and leaving, we will look for the reason for the trouble and find the solution that will address the issue. HighMark Roofing & Construction is in it to stay, and you can trust that we will be there for you when you need it the most!`	`Looking for reliable services to improve our business operations and ensure smooth workflow.`	`0.7`
`Welcome to Pikapet Petshop in Tallahasee, FL 32308, your one-stop destination for all your pet needs! From premium dog grooming services to a wide range of pet supplies, we cater to all your furry friend's requirements. Visit us today for top-quality products and expert grooming services. Your pets deserve the best, and we are here to provide it!`	`Looking for reliable services to improve our business operations and ensure smooth workflow.`	`0.7`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 6
fp16: True
multi_dataset_batch_sampler: round_robin

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
num_train_epochs: 6
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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
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
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	spearman_cosine
1.0	24	0.1424
2.0	48	0.7664
3.0	72	0.8226
4.0	96	0.8387
4.1667	100	0.8438
5.0	120	0.8668
6.0	144	0.8723

Framework Versions

Python: 3.11.13
Sentence Transformers: 4.1.0
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Accelerate: 1.8.1
Datasets: 2.14.4
Tokenizers: 0.21.1

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",
}

	sentence_0	sentence_1	label
type	string	string	float
details	min: 25 tokens mean: 98.46 tokens max: 256 tokens	min: 12 tokens mean: 15.73 tokens max: 20 tokens	min: 0.6 mean: 0.71 max: 0.9

hauzantsaaqif/company_desc_needs

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2