You can deploy this model and start earning money today!

SentenceTransformer based on google-bert/bert-base-uncased

Name: sentest
Availability: InStock

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased on the qqp_triplets 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: google-bert/bert-base-uncased
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- qqp_triplets
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}) with Transformer model: BertModel 
  (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("palusi/sentest")
# Run inference
sentences = [
    'How can I open my computer if I forget my password?',
    'I forget my PC password what should I do to open it?',
    'I forgot my security code on my Nokia 206 how can I unlock it?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Triplet

Dataset: sentest
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9883

Training Details

Training Dataset

qqp_triplets

Dataset: qqp_triplets at f475d9c
Size: 101,762 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: 13.96 tokens
max: 54 tokens
min: 5 tokens
mean: 13.99 tokens
max: 52 tokens
min: 6 tokens
mean: 14.49 tokens
max: 73 tokens

Samples:

anchor	positive	negative
`Who are Mona Punjabi?`	`Who are Mona punjabis?`	`Why are Punjabis so proud of their Punjabi-hood?`
`What are some of the best books on/by Bill Gates?`	`What are the best books of Bill Gates?`	`Are there any films about Bill Gates?`
`Where can I get best pasta in Bangalore?`	`Where can I get best pasta in Bangalore ?`	`Where can I get best street food in Bangalore?`

Loss: TripletLoss with these parameters:
json
1{ 2 "distance_metric": "TripletDistanceMetric.EUCLIDEAN", 3 "triplet_margin": 5 4}

Evaluation Dataset

qqp_triplets

Dataset: qqp_triplets at f475d9c
Size: 101,762 evaluation 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: 13.99 tokens
max: 61 tokens
min: 6 tokens
mean: 13.76 tokens
max: 49 tokens
min: 6 tokens
mean: 14.75 tokens
max: 78 tokens

Samples:

anchor	positive	negative
`How do l study efficiently?`	`How do you study effectively?`	`Why can't I study efficiently?`
`How do you commit suicide?`	`What is the easiest way to commite suicide?`	`What is a way to commit suicide and not damaging your organs so that they can be donated?`
`How do you learn to speak a foreign language?`	`What is the quickest way a person can learn to speak a new language fluently?`	`What's the easiest foreign language for a native English speaker, living in America, to learn to speak?`

Loss: TripletLoss with these parameters:
json
1{ 2 "distance_metric": "TripletDistanceMetric.EUCLIDEAN", 3 "triplet_margin": 5 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
weight_decay: 0.01
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
push_to_hub: True
hub_model_id: palusi/sentest
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: 2e-05
weight_decay: 0.01
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: True
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: True
resume_from_checkpoint: None
hub_model_id: palusi/sentest
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
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_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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	sentest_cosine_accuracy
-1	-1	-	-	0.8806
0.0983	500	2.5691	-	-
0.1965	1000	1.2284	0.6712	0.9645
0.2948	1500	0.8769	-	-
0.3930	2000	0.7151	0.4490	0.9787
0.4913	2500	0.6506	-	-
0.5895	3000	0.5855	0.3519	0.9848
0.6878	3500	0.5397	-	-
0.7860	4000	0.4998	0.3079	0.9871
0.8843	4500	0.4885	-	-
0.9825	5000	0.483	0.288	0.9883

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.2
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.2.0
Tokenizers: 0.21.0

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",
}

TripletLoss

bibtex

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 13.96 tokens max: 54 tokens	min: 5 tokens mean: 13.99 tokens max: 52 tokens	min: 6 tokens mean: 14.49 tokens max: 73 tokens