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

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the generator dataset. 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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 64 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- generator

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': 64, '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): Asym(
    (anchor-0): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
    (positive-0): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  )
)

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("jensjorisdecorte/JobBERT-v2")
# Run inference
sentences = [
    'Branch Manager',
    'teamwork principles, office administration, delegate responsibilities, create banking accounts, manage alarm system, make independent operating decisions, use microsoft office, offer financial services, ensure proper document management, own management skills, use spreadsheets software, manage cash flow, integrate community outreach, manage time, perform multiple tasks at the same time, carry out calculations, assess customer credibility, maintain customer service, team building, digitise documents, promote financial products, communication, assist customers, follow procedures in the event of an alarm, office equipment',
    'support employability of people with disabilities, schedule shifts, issue licences, funding methods, maintain correspondence records, computer equipment, decide on providing funds, tend filing machine, use microsoft office, lift stacks of paper, transport office equipment, tend to guests with special needs, provide written content, foreign affairs policy development, provide charity services, philanthropy, maintain financial records, meet deadlines, manage fundraising activities, assist individuals with disabilities in community activities, report on grants, prepare compliance documents, manage grant applications, tolerate sitting for long periods, follow work schedule',
]
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

generator

Dataset: generator
Size: 5,579,240 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 3 tokens
mean: 7.95 tokens
max: 30 tokens

min: 18 tokens
mean: 59.33 tokens
max: 64 tokens

	anchor	positive
type	string	string
details	min: 3 tokens mean: 7.95 tokens max: 30 tokens	min: 18 tokens mean: 59.33 tokens max: 64 tokens

Samples:

anchor	positive
`CAD Designer - Fire Sprinkler - Milwaukee - Relocation`	`coordinate construction activities, oversee construction project, fire protection engineering, install fire sprinklers, hydraulics, construction industry, create AutoCAD drawings, design sprinkler systems, inspect construction sites, design drawings, supervise sewerage systems construction, prepare site for construction, building codes, communicate with construction crews`
`RN Practitioner`	assume responsibility, financial statements, manage work, implement fundamentals of nursing, diagnose advanced nursing care, diagnose nursing care, specialist nursing care, nursing principles, provide nursing advice on healthcare, apply nursing care in long-term care, prescribe advanced nursing care, plan advanced nursing care, nursing science, implement nursing care, develop financial statistics reports, clinical decision-making at advanced practice, prepare financial statements, create a financial report, produce statistical financial records, operate in a specific field of nursing care
`Respiratory Therapist Travel Positions (BB-160B7)`	`respiratory therapy, comply with quality standards related to healthcare practice, provide information, primary care, record treated patient's information, formulate a treatment plan, carry out treatment prescribed by doctors, develop patient treatment strategies`

Loss: CachedMultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

overwrite_output_dir: True
per_device_train_batch_size: 2048
per_device_eval_batch_size: 2048
num_train_epochs: 1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: True
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 2048
per_device_eval_batch_size: 2048
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: 0.0
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: 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
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss
0.1835	500	3.6354
0.3670	1000	3.1788
0.5505	1500	2.9969
0.7339	2000	2.9026
0.9174	2500	2.8421

Framework Versions

Python: 3.9.19
Sentence Transformers: 3.1.0
Transformers: 4.44.2
PyTorch: 2.4.1+cu118
Accelerate: 0.34.2
Datasets: 3.0.0
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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

jensjorisdecorte
/

JobBERT-v2