metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2860
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: >-
      No, it is not true. The sex chromosomes of the father determine the sex of
      an unborn baby, not the mother.
    sentences:
      - >-
        The wall of the uterus expands outward like a balloon during ovum
        maturation.
      - >-
        The mother's emotional state during pregnancy can influence the sex of
        the baby, making her solely responsible for determining it.
      - Six
  - source_sentence: Answer not found in response.
    sentences:
      - nan
      - >-
        In living organisms, cells are likened to bricks in a building due to
        their role as structural components.
      - >-
        Plant cells exclusively house chloroplasts as they play a crucial role
        in converting sunlight into energy for plants through the process of
        photosynthesis. These specialized organelles possess chlorophyll, a
        green pigment essential for absorbing light energy.
  - source_sentence: >-
      The organelles found in the cytoplasm of a cell include mitochondria,
      golgi bodies, ribosomes, and other components.
    sentences:
      - >-
        Examples of diseases that vaccines offer protection from are cholera,
        tuberculosis, smallpox, and hepatitis.
      - >-
        Having a balanced diet helps regulate the levels of fairy dust in the
        body, which indirectly impacts reproductive health.
      - >-
        Mitochondria, golgi bodies, ribosomes, and various other structures are
        present in the cytoplasm of a cell.
  - source_sentence: >-
      The basic practices of crop production include preparation of soil,
      sowing, adding manure and fertilizers, irrigation, protecting from weeds,
      harvesting, and storage.
    sentences:
      - You can see miniature plants growing inside the water droplet.
      - >-
        Changes in their natural surroundings, such as deforestation and
        desertification, cause migratory birds to fly to distant areas,
        impacting their access to food, places for breeding, and the overall
        ecosystem.
      - >-
        Essential tasks involved in crop cultivation consist of priming the
        soil, planting seeds, applying fertilizers and manure, providing water,
        preventing weed growth, collecting the crops, and storing them.
  - source_sentence: >-
      The embryo gets embedded in the wall of the uterus for further development
      after fertilisation.
    sentences:
      - >-
        By recycling paper, the need for harvesting trees for paper production
        can be significantly reduced, leading to conservation of trees, energy,
        and water, as well as minimizing the use of harmful chemicals in the
        paper-making process.
      - >-
        In the rainy season, if you examine moist bread, you may see greyish
        white spots that are adorned with minuscule, black circular shapes,
        believed to be microorganisms that have thrived on the bread.
      - >-
        Following fertilization, the embryo attaches to the uterine wall to
        progress in its development.

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

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 tokens
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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("msamg/sts_qna_model")
# Run inference
sentences = [
    'The embryo gets embedded in the wall of the uterus for further development after fertilisation.',
    'Following fertilization, the embryo attaches to the uterine wall to progress in its development.',
    'By recycling paper, the need for harvesting trees for paper production can be significantly reduced, leading to conservation of trees, energy, and water, as well as minimizing the use of harmful chemicals in the paper-making process.',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 2,860 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 8 tokens
mean: 40.09 tokens
max: 225 tokens

min: 3 tokens
mean: 26.95 tokens
max: 112 tokens

min: 0.0
mean: 0.41
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 8 tokens mean: 40.09 tokens max: 225 tokens	min: 3 tokens mean: 26.95 tokens max: 112 tokens	min: 0.0 mean: 0.41 max: 1.0

Samples:

sentence_0	sentence_1	label
`To identify the cell membrane, cytoplasm, and nucleus under a microscope when observing cheek cells, you can look for the cell membrane as the outer boundary of the cell, the cytoplasm which is the jelly-like substance between the cell membrane and the nucleus, and the nucleus which is usually darker and located in the center of the cell. Additionally, remember that animal cells do not have a cell wall.`	`When examining cheek cells under a microscope, you should be able to distinguish the cell membrane, which forms the outer layer, the cytoplasm, which is a gel-like material surrounding the nucleus, and the nucleus, located centrally and typically darker in appearance. It's important to note that animal cells lack a cell wall.`	`1.0`
`The development of the embryo in oviparous animals takes place inside the egg shell.`	`The development of the embryo in oviparous animals takes place in the mother's pouch.`	`0.0`
`Answer not found in response.`	`nan`	`1.0`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
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
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: 1
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: False
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: 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_eval_metrics: False
eval_on_start: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Framework Versions

Python: 3.11.3
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cpu
Accelerate: 0.32.1
Datasets: 2.20.0
Tokenizers: 0.19.1

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",
}