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 retrieval.

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
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'MPNetModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Data Scientist with 1 years working across active teams. Demonstrated technical execution and history background includes: Py3 Engine, PostgreSQL, Theoretical knowledge of ML, GenAI. Seeking an engineering position to scale architectural patterns.',
    'We are looking for a Quantitative Analytics Expert with a minimum of 4+ years of experience. The core technical stack requirements involve deep knowledge in: Py3 Engine, Postgres, Machine Learning, GenAI, Amazon Web Services. Must be highly capable of executing product deliverables in a fast paced workspace environment.',
    'Seeking a skilled Senior React Native Mobile Architect to join our growing team. Key responsibilities include building robust declarative modular application structures that map perfectly across target runtime layers. Must be fully comfortable handling tools like Mobile UI render optimization configurations, component lifecycles, and component scaling metrics in a fast-paced environment.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4431, 0.1849],
#         [0.4431, 1.0000, 0.4543],
#         [0.1849, 0.4543, 1.0000]])

Evaluation

Metrics

Semantic Similarity

• Dataset: ats-val
• Evaluated with EmbeddingSimilarityEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 6,790 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 100 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  modality	text	text
  details	min: 36 tokensmean: 57.5 tokensmax: 75 tokens	min: 58 tokensmean: 67.02 tokensmax: 76 tokens	min: 0.02mean: 0.66max: 0.99

• Samples:

  sentence_0	sentence_1	label
  Lead Data Scientist bringing over 8 years of industry experience along with a verified Masters degree. Expert competencies cover Python data ecosystems, custom Pandas metrics, NumPy, and advanced SQL matrices. Proven success track record in optimizing complex optimization layers to surface implicit correlation parameters across structures.	Seeking a skilled Financial Quantitative Portfolio Analyst to join our growing team. Key responsibilities include modeling volatile financial vectors to predict historical risk exposure trends. Must be fully comfortable handling tools like Advanced quantitative modeling systems, predictive alpha signals generation, and mathematical metrics in a fast-paced environment.	0.8923
  Gastronomy Chef Specialist bringing over 9 years of industry experience along with a verified Bachelors degree. Expert competencies cover Kitchen management, menu engineering, and food safety protocols. Proven success track record in authoring seasonal menus while maintaining strict cost-of-goods compliance audits.	Seeking a skilled Statistical Modeling Specialist to join our growing team. Key responsibilities include extracting tabular feature data matrices to surface corporate risk exposures. Must be fully comfortable handling tools like dbt data warehousing modeling, Snowflake, Pandas analytics, and statistical hypothesis tracking in a fast-paced environment.	0.0229
  Modern JavaScript Systems Engineer bringing over 7 years of industry experience along with a verified Masters degree. Expert competencies cover TypeScript application scaling, component modular patterns, and performance tuning. Proven success track record in abstracting core layout state patterns into reusable, contextually driven modular hooks.	Seeking a skilled Cross-Platform Mobile Engineer to join our growing team. Key responsibilities include optimizing responsive visual components to enforce smooth multi-device execution footprints. Must be fully comfortable handling tools like React Native declarative code paradigms, mobile layout state setups, and native bridges in a fast-paced environment.	0.9061

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss",
      "cos_score_transformation": "torch.nn.modules.linear.Identity"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• num_train_epochs: 4
• per_device_eval_batch_size: 16
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

• per_device_train_batch_size: 16
• num_train_epochs: 4
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1
• label_smoothing_factor: 0.0
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 16
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 14.7 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.5.1
• Transformers: 5.10.2
• PyTorch: 2.11.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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",
}