model/README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:19992
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: |-
      Role: Full Stack Engineer
      Skills: JavaScript, APIs, React, Databases, Node.js
    sentences:
      - |-
        Job Title: Product Manager
        Skills: Roadmap, Stakeholders, PRD, Agile, Strategy
      - |-
        Job Title: Full Stack Engineer
        Skills: JavaScript, APIs, React, Databases, Node.js
      - |-
        Job Title: Full Stack Engineer
        Skills: JavaScript, APIs, React, Databases, Node.js
  - source_sentence: |-
      Role: Mechanical Engineer
      Skills: CAD, Thermodynamics, Manufacturing
    sentences:
      - |-
        Job Title: Frontend Engineer
        Skills: JavaScript, React, CSS, HTML, UI
      - |-
        Job Title: Operations Manager
        Skills: KPIs, Process Improvement, Planning, Stakeholders
      - |-
        Job Title: Mechanical Engineer
        Skills: CAD, Thermodynamics, Manufacturing
  - source_sentence: |-
      Role: Backend Engineer
      Skills: Python, APIs, Databases, Docker, OOP
    sentences:
      - |-
        Job Title: Full Stack Engineer
        Skills: JavaScript, APIs, React, Databases, Node.js
      - |-
        Job Title: Backend Engineer
        Skills: Python, APIs, Databases, Docker, OOP
      - |-
        Job Title: Backend Engineer
        Skills: Python, APIs, Databases, Docker, OOP
  - source_sentence: |-
      Role: Civil Engineer
      Skills: AutoCAD, Structural Analysis, Construction, Planning
    sentences:
      - |-
        Job Title: Mechanical Engineer
        Skills: CAD, Thermodynamics, Manufacturing
      - |-
        Job Title: Mechanical Engineer
        Skills: CAD, Thermodynamics, Manufacturing
      - |-
        Job Title: Civil Engineer
        Skills: AutoCAD, Structural Analysis, Construction, Planning
  - source_sentence: |-
      Role: Data Scientist
      Skills: Python, Statistics, Pandas, ML, Visualization, Modeling
    sentences:
      - |-
        Job Title: Mechanical Engineer
        Skills: CAD, Thermodynamics, Manufacturing
      - |-
        Job Title: Data Scientist
        Skills: Python, Statistics, Pandas, ML, Visualization, Modeling
      - |-
        Job Title: Civil Engineer
        Skills: AutoCAD, Structural Analysis, Construction, Planning
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer

This is a sentence-transformers model trained. 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
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• 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, 'architecture': '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Role: Data Scientist\nSkills: Python, Statistics, Pandas, ML, Visualization, Modeling',
    'Job Title: Data Scientist\nSkills: Python, Statistics, Pandas, ML, Visualization, Modeling',
    'Job Title: Civil Engineer\nSkills: AutoCAD, Structural Analysis, Construction, Planning',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9988, 0.2972],
#         [0.9988, 1.0000, 0.3066],
#         [0.2972, 0.3066, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 19,992 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: 16 tokens mean: 19.8 tokens max: 27 tokens	min: 17 tokens mean: 20.8 tokens max: 28 tokens

• Samples:

  sentence_0	sentence_1
  Role: Operations Manager Skills: KPIs, Process Improvement, Planning, Stakeholders	Job Title: Operations Manager Skills: KPIs, Process Improvement, Planning, Stakeholders
  Role: Frontend Engineer Skills: JavaScript, React, CSS, HTML, UI	Job Title: Frontend Engineer Skills: JavaScript, React, CSS, HTML, UI
  Role: Full Stack Engineer Skills: JavaScript, APIs, React, Databases, Node.js	Job Title: Full Stack Engineer Skills: JavaScript, APIs, React, Databases, Node.js

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 96
• per_device_eval_batch_size: 96
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• per_device_train_batch_size: 96
• num_train_epochs: 3
• 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: trackio
• eval_strategy: no
• per_device_eval_batch_size: 96
• 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_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• 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

Epoch	Step	Training Loss
2.3923	500	2.2303

Framework Versions

• Python: 3.12.7
• Sentence Transformers: 5.3.0
• Transformers: 5.3.0
• PyTorch: 2.10.0+cu130
• Accelerate: 1.13.0
• Datasets: 4.7.0
• 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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}