metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2437
  - loss:ContrastiveLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: >-
      I am having troubles and confusing moments with my body and I am scared I
      may be pregnant by my research online and I really want some advice ?
    sentences:
      - 'Does Acyclovir cause ulcers when it is prescribed for genital herpes? '
      - >-
        The confusing symptoms and online research points towards me being
        pregnant. Can I get a professional advice?
      - >-
        Do bariatric surgeries like gastric sleeve or Roux-en-Y surgery actually
        work in the long term?
  - source_sentence: >-
      It started with a headache the next day came dizziness when I move my
      eyes, soreness behind my eyes, 102 fever, slight cough. Help!
    sentences:
      - >-
        I had a headache and this was followe by dizziness on moving the eyes,
        soreness behind my eyes, high grade fever (102) and slight cough. Can
        you help me?
      - What are the signs of ovulation?
      - >-
        Why does it hurt when I shave my face? Can I do something else for it
        besides shaving in the direction of the hair growth?
  - source_sentence: How low can hemoglobin go before you need a transfusion?
    sentences:
      - >-
        I heard banana is rich in potassium. I am having diarrhea and can I take
        banana. 
      - At what Hemoglobin levels, is a blood transfusion recommended?
      - What are the symptoms of eye cancer?
  - source_sentence: >-
      I'm 5 weeks pregnant and this morning had brownish spotting, my gyn said
      this is normal and ita was due to implantation, should I be worried?
    sentences:
      - >-
        I have abdominal cramps, spotting, nause and fatigue. I am on oral
        contraceptive pills. I take them regularly. My pregnancy test is
        negative. I dont believe it is implantation as I am not pregnant. Could
        it be withdrawal bleeding or do I have an STD?
      - 'What''s best for a 1 year old, breast milk or bottle milk? '
      - >-
        I am 40, and I've had a breast lump in my right breast for about 4 years
        now. Could it be cancer?
  - source_sentence: >-
      My bm aren't solid but not quite loose. Looks more like for lack of better
      word "shredded" the why is this?
    sentences:
      - >-
        I have been taking treatment for anxiety and depression. I was given a
        new medication and have experienced heart flutters, can this medication
        cause it?
      - >-
        You might think I'm a bit paranoid but could you please help me with the
        five most common emergency surgeries in american teen girls?
      - What causes stringy and shredded stools?
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: all mqp test
          type: all-mqp-test
        metrics:
          - type: cosine_accuracy
            value: 0.8786885245901639
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.7678120136260986
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.8796147672552167
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.7446306943893433
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.8810289389067524
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8782051282051282
            name: Cosine Recall
          - type: cosine_ap
            value: 0.9474266832530879
            name: Cosine Ap

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("mpnet-base-all-mqp-binary")
# Run inference
sentences = [
    'My bm aren\'t solid but not quite loose. Looks more like for lack of better word "shredded" the why is this?',
    'What causes stringy and shredded stools?',
    'I have been taking treatment for anxiety and depression. I was given a new medication and have experienced heart flutters, can this medication cause 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

Binary Classification

Dataset: all-mqp-test
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8787
cosine_accuracy_threshold	0.7678
cosine_f1	0.8796
cosine_f1_threshold	0.7446
cosine_precision	0.881
cosine_recall	0.8782
cosine_ap	0.9474

Training Details

Training Dataset

Unnamed Dataset

Size: 2,437 training samples
Columns: text1, text2, and label
Approximate statistics based on the first 1000 samples:
text1 text2 label
type string string int
details
min: 7 tokens
mean: 26.53 tokens
max: 75 tokens

min: 7 tokens
mean: 28.18 tokens
max: 119 tokens

0: ~49.00%
1: ~51.00%

	text1	text2	label
type	string	string	int
details	min: 7 tokens mean: 26.53 tokens max: 75 tokens	min: 7 tokens mean: 28.18 tokens max: 119 tokens	0: ~49.00% 1: ~51.00%

Samples:

text1	text2	label
`I discovered I get this weakness in my hand whenever I try to snap my fingers, slight pain runs across elbow and wrist?`	`When I try to snap my fingers there is weakness and pain across elbow and wrist? May I know what are the causes?`	`1`
`If a mother has celiac should the daughter be tested?`	`What is Celiac disease?`	`0`
`Hi im 18 and I would like to know what I would use or take to get taller?`	`Can growth hormone taken in minimal quantities increase height after 21 years in a male?`	`0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Evaluation Dataset

Unnamed Dataset

Size: 610 evaluation samples
Columns: text1, text2, and label
Approximate statistics based on the first 610 samples:
text1 text2 label
type string string int
details
min: 8 tokens
mean: 27.56 tokens
max: 70 tokens

min: 8 tokens
mean: 27.88 tokens
max: 91 tokens

0: ~48.85%
1: ~51.15%

	text1	text2	label
type	string	string	int
details	min: 8 tokens mean: 27.56 tokens max: 70 tokens	min: 8 tokens mean: 27.88 tokens max: 91 tokens	0: ~48.85% 1: ~51.15%

Samples:

text1	text2	label
`Okay so i'm on bc and I have had sex (it hurts) i'm bleeding brown and my vagina hurts almost itchy but it hurts?`	`I noticed a brown discharge and itching in my vaginal area to the point that it hurts. I am also on birth control and have sexual intercourse. What do you think is causing this?`	`1`
`I've had body aches, blocked stuffy nose, headaches, pressure in my face and throat tightness and it feels dry for 6 months is it a bad cold?`	`For the last 6 months, I've noticed symptoms like body aches, stuffy nose, headaches, pressure sensation in the face, throat tightness and feels dry. Can a cold last this long or should I be looking for something else?`	`1`
`Is there any way to stop my period for a little while without a prescription?`	`Are there any natural ways to stop my period without having to visit a local doctor?`	`1`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

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
push_to_hub: 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: True
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
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	all-mqp-test_cosine_ap
0.6536	100	0.0137	0.0135	-
1.0	153	-	-	0.9474

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.3.1
Transformers: 4.47.1
PyTorch: 2.6.0+cu124
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.0

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}