metadata

base_model: sentence-transformers/all-mpnet-base-v2
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:178829
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: who was actor larry parks
    sentences:
      - >-
        American stage and movie actor.e eventually did so in tears, only to be
        blacklisted anyway.
      - >-
        A possum (plural form: possums) is any of about 70 small-to medium-sized
        arboreal marsupial species native to Australia, New Guinea, and Sulawesi
        (and introduced to New Zealand and China). The common brushtail possum
        was introduced to New Zealand by European settlers in an attempt to
        establish a fur industry. There are no native predators of the possum in
        New Zealand, so its numbers in New Zealand have risen to the point where
        it is considered a serious pest.
      - >-
        A document used to change one or more minor provisions of a living trust
        or joint living trust as an alternative to preparing a new living trust.
  - source_sentence: what is the salary of a person with a biology degree
    sentences:
      - $10 to $25 per hour.
      - $25,290 (2014-2015 academic year)
      - >-
        Biology majors who don’t attend a graduate program make a median salary
        of $51,000 per year, which is a little below the median salary for
        graduates from all other majors combined. Don’t let that fact stop you
        from pursuing a degree in biology if it’s what you’re passionate about,
        though. Career Options for Biology Majors. Below is a list of common
        career options for biology majors. This isn’t a comprehensive list, as
        students who major in biology go on to do many interesting things.
        However, this list should give you an idea of the types of work that
        would be available to you with a degree in biology.
  - source_sentence: definition of pretext
    sentences:
      - >-
        Peanut butter is an excellent source of nutrition. Required to contain
        at least 90 percent peanuts, it includes more than 30 vitamins and
        minerals. Peanut butter contains no cholesterol or trans fats, according
        to the National Peanut Board. In fact, studies show that peanut butter
        may even improve your levels of good cholesterol.
      - >-
        Pretext generally refers to a reason for an action which is false, and
        offered to cover up true motives or intentions. It is a concept
        sometimes brought up in the context of employment discrimination.
      - 20.5 degrees Celsius (68.8 degrees Fahrenheit).
  - source_sentence: what is cyber spoofing
    sentences:
      - >-
        Once your question has been posted for at least 1 hour and has at least
        one answer, click on 'Award Best Answer' button next to your chosen
        answer. 1 Upload failed. 2 Please upload a file larger than 100x100
        pixels. 3 We are experiencing some problems, please try again.
      - >-
        Though some vegetable sources of protein contain sufficient values of
        all essential amino acids, many are lower in one or more essential amino
        acids than animal sources, especially lysine, and to a lesser extent
        methionine and threonine. 1 Proteins derived from plant foods (legumes,
        seeds, grains, and vegetables) can be complete as well (examples include
        chickpeas, black beans, pumpkin seeds, cashews, cauliflower, quinoa,
        pistachios, turnip greens, black-eyed peas, and soy). 2  Most plant
        foods tend to have less of one or more essential amino acid
      - >-
        A spoofing attack is a situation in which one person or program
        successfully masquerades as another by falsifying data and thereby
        gaining an illegitimate advantage.
  - source_sentence: what type of reaction is iron plus oxygen
    sentences:
      - Pearl
      - 'Yes'
      - >-
        When a metal undergos a combination reaction with oxygen, a metal oxide
        is formed (similarily, a metal halide is formed if reacted with one of
        the halogens). You see the products of this type of reaction whenever
        you see rust. Rust is the product of a combination reaction of iron and
        oxygen:

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 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': 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("DashReza7/all-mpnet-base-v2_FINETUNED")
# Run inference
sentences = [
    'what type of reaction is iron plus oxygen',
    'When a metal undergos a combination reaction with oxygen, a metal oxide is formed (similarily, a metal halide is formed if reacted with one of the halogens). You see the products of this type of reaction whenever you see rust. Rust is the product of a combination reaction of iron and oxygen: ',
    'Pearl',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 178,829 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 5 tokens
mean: 9.37 tokens
max: 22 tokens

min: 3 tokens
mean: 60.48 tokens
max: 197 tokens

	anchor	positive
type	string	string
details	min: 5 tokens mean: 9.37 tokens max: 22 tokens	min: 3 tokens mean: 60.48 tokens max: 197 tokens

Samples:

anchor	positive
`what is rba`	`Results-Based Accountability is a disciplined way of thinking and taking action that communities can use to improve the lives of children, youth, families, adults and the community as a whole.`
`what is rba`	Results-Based Accountability® (also known as RBA) is a disciplined way of thinking and taking action that communities can use to improve the lives of children, youth, families, adults and the community as a whole. RBA is also used by organizations to improve the performance of their programs. Creating Community Impact with RBA. Community impact focuses on conditions of well-being for children, families and the community as a whole that a group of leaders is working collectively to improve. For example: “Residents with good jobs,” “Children ready for school,” or “A safe and clean neighborhood”.
`was ronald reagan a democrat`	`Yes`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 64
per_device_eval_batch_size: 64
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
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: 2e-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: 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: proportional

Training Logs

Epoch	Step	Training Loss
0.1789	500	0.279
0.3578	1000	0.2194
0.5367	1500	0.21
0.7156	2000	0.207
0.8945	2500	0.198

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cu121
Accelerate: 0.32.1
Datasets: 2.21.0
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",
}

MultipleNegativesRankingLoss

@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}
}