metadata

base_model: mixedbread-ai/mxbai-embed-large-v1
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:7704
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: |-
      Serve food or beverages.
      Provide customers with general information or assistance.
      Clean facilities or work areas.
    sentences:
      - |-
        Assess database performance.
        Analyze data to identify trends or relationships among variables.
        Develop procedures for data management.
        Create databases to store electronic data.
        Design computer modeling or simulation programs.
      - >-
        Feed, water, groom, bathe, exercise, or otherwise provide care to
        promote and maintain the well-being of pets and other animals that are
        not raised for consumption, such as dogs, cats, race horses, ornamental
        fish or birds, zoo animals, and mice. Work in settings such as kennels,
        animal shelters, zoos, circuses, and aquariums. May keep records of
        feedings, treatments, and animals received or discharged. May clean,
        disinfect, and repair cages, pens, or fish tanks.
      - >-
        Dining Room and Cafeteria Attendants and Bartender Helpers - Facilitate
        food service. Clean tables; remove dirty dishes; replace soiled table
        linens; set tables; replenish supply of clean linens, silverware,
        glassware, and dishes; supply service bar with food; and serve items
        such as water, condiments, and coffee to patrons.
  - source_sentence: >-
      Supervise staff, volunteers, practicum students, or interns.

      Teach art therapy techniques or processes to artists, interns, volunteers,
      or others.

      Photograph or videotape client artwork for inclusion in client records or
      for promotional purposes.

      Establish goals or objectives for art therapy sessions in consultation
      with clients or site administrators.
    sentences:
      - >-
        Financial Managers - Analyze financial records to improve budgeting or
        planning.

        Supervise employees.

        Prepare reports related to compliance matters.

        Direct organizational operations, projects, or services.

        Establish interpersonal business relationships to facilitate work
        activities.
      - >-
        Plan or conduct art therapy sessions or programs to improve clients'
        physical, cognitive, or emotional well-being.
      - |-
        Maintain operational records.
        Manage organizational or project budgets.
        Develop promotional materials.
        Analyze risks to minimize losses or damages.
  - source_sentence: >-
      Tire Repairers and Changers - Disassemble equipment for maintenance or
      repair.

      Service vehicles to maintain functionality.

      Assemble mechanical components or machine parts.
    sentences:
      - >-
        Select, fit, and take care of costumes for cast members, and aid
        entertainers. May assist with multiple costume changes during
        performances.
      - |-
        Install metal structural components.
        Cut metal components for installation.
        Position safety or support equipment.
        Operate cranes, hoists, or other moving or lifting equipment.
        Position structural components.
      - |-
        Disassemble equipment for maintenance or repair.
        Service vehicles to maintain functionality.
        Assemble mechanical components or machine parts.
  - source_sentence: |-
      Orthodontists - Adjust dental devices or appliances to ensure fit.
      Confer with clients to discuss treatment plans or progress.
      Design medical devices or appliances.
      Train medical providers.
      Advise patients on effects of health conditions or treatments.
    sentences:
      - |-
        Maintain surveillance of individuals or establishments.
        Apprehend criminal suspects.
        Recommend improvements to increase safety or reduce risks.
        Administer first aid.
        Communicate health and wellness information to the public.
        Confiscate prohibited or dangerous items.
      - |-
        Build models, patterns, or templates.
        Operate still or video cameras or related equipment.
        Prepare materials for preservation, storage, or display.
        Estimate costs for projects or productions.
        Coordinate logistics for productions or events.
        Perform marketing activities.
      - |-
        Adjust dental devices or appliances to ensure fit.
        Confer with clients to discuss treatment plans or progress.
        Design medical devices or appliances.
        Train medical providers.
        Advise patients on effects of health conditions or treatments.
  - source_sentence: >-
      Collect samples of materials or products for laboratory testing.

      Weigh or measure materials, ingredients, or products to ensure conformance
      to requirements.

      Stop mixing or blending machines when specified product qualities are
      obtained and open valves and start pumps to transfer mixtures.
    sentences:
      - >-
        Load materials into production equipment.

        Clear equipment jams.

        Test chemical or physical characteristics of materials or products.

        Mix substances to create chemical solutions.

        Adjust equipment controls to regulate flow of production materials or
        products.

        Clean facilities or work areas.
      - >-
        Provide services to ensure the safety of passengers aboard ships, buses,
        trains, or within the station or terminal. Perform duties such as
        explaining the use of safety equipment, serving meals or beverages, or
        answering questions related to travel.
      - |-
        Conduct research to increase knowledge about medical issues.
        Evaluate patient functioning, capabilities, or health.
        Collaborate with healthcare professionals to plan or provide treatment.
        Maintain inventory of medical supplies or equipment.
        Process medical billing information.
        Clean facilities or equipment.

SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1

This is a sentence-transformers model finetuned from mixedbread-ai/mxbai-embed-large-v1. It maps sentences & paragraphs to a 1024-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: mixedbread-ai/mxbai-embed-large-v1
Maximum Sequence Length: 128 tokens
Output Dimensionality: 1024 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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Daxtra/onet_sbert-v3")
# Run inference
sentences = [
    'Collect samples of materials or products for laboratory testing.\nWeigh or measure materials, ingredients, or products to ensure conformance to requirements.\nStop mixing or blending machines when specified product qualities are obtained and open valves and start pumps to transfer mixtures.',
    'Load materials into production equipment.\nClear equipment jams.\nTest chemical or physical characteristics of materials or products.\nMix substances to create chemical solutions.\nAdjust equipment controls to regulate flow of production materials or products.\nClean facilities or work areas.',
    'Conduct research to increase knowledge about medical issues.\nEvaluate patient functioning, capabilities, or health.\nCollaborate with healthcare professionals to plan or provide treatment.\nMaintain inventory of medical supplies or equipment.\nProcess medical billing information.\nClean facilities or equipment.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Training Details

Training Dataset

Unnamed Dataset

Size: 7,704 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 13 tokens
mean: 70.86 tokens
max: 128 tokens

min: 9 tokens
mean: 41.53 tokens
max: 115 tokens

	sentence_0	sentence_1
type	string	string
details	min: 13 tokens mean: 70.86 tokens max: 128 tokens	min: 9 tokens mean: 41.53 tokens max: 115 tokens

Samples:

sentence_0	sentence_1
`Textile Knitting and Weaving Machine Setters, Operators, and Tenders - Record operational or production data. Lubricate production equipment. Conduct test runs of production equipment. Clean production equipment. Repair production equipment or tools.`	`Record operational or production data. Lubricate production equipment. Conduct test runs of production equipment. Clean production equipment. Repair production equipment or tools.`
`Provide technical support for software maintenance or use. Evaluate data quality. Update knowledge about emerging industry or technology trends. Prepare analytical reports. Collaborate with others to resolve information technology issues. Troubleshoot issues with computer applications or systems.`	`Geographic Information Systems Technologists and Technicians - Assist scientists or related professionals in building, maintaining, modifying, or using geographic information systems (GIS) databases. May also perform some custom application development or provide user support.`
`Prepare pointe shoes, by sewing or other means, for use in rehearsals and performance. Attend costume fittings, photography sessions, and makeup calls associated with dance performances. Perform classical, modern, or acrobatic dances in productions, expressing stories, rhythm, and sound with their bodies. Devise and choreograph dance for self or others. Study and practice dance moves required in roles. Monitor the field of dance to remain aware of current trends and innovations.`	`Train others on performance techniques. Perform dances. Audition for roles. Choreograph dances. Monitor current trends.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 24
per_device_eval_batch_size: 24
num_train_epochs: 1
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: 24
per_device_eval_batch_size: 24
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: 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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step
0.0997	32
0.1994	64
0.2991	96
0.3988	128
0.4984	160
0.5981	192
0.6978	224
0.7975	256
0.8972	288
0.9969	320
1.0	321

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.0
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.34.2
Datasets: 3.0.1
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}
}