---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:114699
- loss:CachedGISTEmbedLoss
base_model: BAAI/bge-large-en-v1.5
widget:
- source_sentence: For roles such as 'physiotherapist', 'neuromusculoskeletal physiotherapist',
'osteopath', and 'chiropractor', the skills needed include a deep understanding
of human anatomy and physiology, strong diagnostic skills, and the ability to
apply manual therapy techniques to treat musculoskeletal issues. Additionally,
effective communication skills are crucial for explaining treatments and exercises
to patients, while adaptability and problem-solving skills are essential for tailoring
treatments to individual patient needs.
sentences:
- Job roles such as insulation installers, HVAC technicians, and construction engineers
require knowledge of various types and characteristics of insulation materials
to effectively reduce heat transfer and improve energy efficiency in buildings
and systems. Understanding the typology of insulation materials, including their
thermal properties, durability, and environmental impact, is crucial for these
professionals to select the most appropriate materials for specific applications.
- Job roles such as Contract Managers, Legal Analysts, and Compliance Officers require
the skill of reviewing or auditing completed contracts to ensure legal accuracy,
compliance with regulations, and alignment with organizational goals.
- Job roles that require skills in dealing with emergency care situations include
emergency medical technicians (EMTs), paramedics, and emergency room nurses or
doctors, all of whom must quickly and effectively manage critical health situations
to save lives.
- source_sentence: Bus drivers, including those operating in various sectors like
public transit, intercity, private, or school services, need strong driving skills,
knowledge of traffic laws, and the ability to operate safely in diverse conditions.
Additionally, effective communication skills and the ability to handle passenger
inquiries and emergencies are crucial.
sentences:
- Job roles that require the skill to calibrate electronic instruments include calibration
technicians, quality control engineers, and instrumentation specialists. These
professionals ensure the accuracy and reliability of various electronic devices
and systems across different industries such as manufacturing, aerospace, and
automotive.
- Job roles such as Building Engineer, Architect, and Construction Specialist require
skills in designing, engineering, or developing air-tight building structures
to ensure energy efficiency and environmental control within the building.
- Job roles such as customer service representatives, flight attendants, and hotel
concierges require a strong focus on passengers or customers, ensuring their needs
and comfort are prioritized to provide excellent service and support.
- source_sentence: A mine surveyor, also known as a mining surveyor or mine planning
surveyor, requires expertise in geomatics and mining engineering to accurately
map and plan mine operations, ensuring safety and efficiency. They must also possess
strong analytical skills and the ability to use specialized software for creating
detailed mine plans and maintaining accurate records.
sentences:
- Job roles such as data analysts, business analysts, and financial analysts require
the skill to present reports or prepare statistical reports, as they often need
to communicate complex data insights clearly and effectively to stakeholders.
- Job roles that require monitoring flour unloading equipment include Quality Control
Technicians, Process Operators, and Mill Supervisors, who ensure the efficient
and safe operation of flour processing systems and the proper unloading of flour
from transport vehicles.
- Job roles that require skills in the manufacturing of made-up textile articles
include textile production managers, machinery operators, and quality control
inspectors, all of whom utilize specific technology and machinery to produce finished
textile products such as clothing, home textiles, and industrial fabrics.
- source_sentence: An insulation supervisor, regardless of the specific type of insulation
material or installation area, requires strong project management skills, knowledge
of building codes and safety regulations, and expertise in insulation techniques
to oversee the installation process effectively and ensure quality standards are
met.
sentences:
- Job roles that require skills in energy efficiency, such as promoting energy efficiency
or efficient energy use, include Energy Managers, Sustainability Specialists,
and Building Engineers, who focus on reducing energy consumption and improving
energy use in various settings. Additionally, roles like Battery Technicians or
Engineers involve battery benchmarking to enhance energy storage and efficiency
in technological devices and systems.
- The skill of applying or installing waterproofing and damp-proofing membranes
is primarily required by construction workers such as waterproofing specialists,
roofers, and building envelope technicians, who use these membranes to prevent
water damage in buildings and structures.
- Job roles such as laboratory technicians, chemists, and materials scientists require
skills in laboratory techniques, including electronic and thermic methods, gas
chromatography, and gravimetric analysis, to conduct precise experiments and analyze
materials. These professionals must apply natural science techniques and use various
lab techniques to ensure accurate and reliable results in their research or quality
control processes.
- source_sentence: For roles such as import/export manager, graduate export manager,
senior export manager, and other related positions in meat and meat products,
the key skills include a strong understanding of international trade regulations,
meat product knowledge, customs compliance, and excellent negotiation and communication
skills to manage global supply chains effectively. Additionally, proficiency in
relevant trade software and languages can be highly beneficial.
sentences:
- Job roles that require skills such as managing staff, coordinating employees,
and performing HR activities include Human Resources Managers, Team Leaders, Supervisors,
and Department Heads, all of whom are responsible for overseeing personnel, implementing
HR policies, and ensuring efficient team operations.
- Job roles such as Control Systems Engineer, Automation Engineer, and Systems Designer
require skills in designing, planning, and developing control systems to manage
and optimize the performance of various technological processes and machinery.
These professionals are tasked with creating efficient and reliable systems that
can operate autonomously or with minimal human intervention.
- Job roles such as Performance Analyst, Quality Assurance Engineer, and Test Manager
require skills in conducting performance measurement and organizing or managing
conversion testing to ensure software and systems meet performance standards and
function correctly in real-world scenarios.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@20
- cosine_accuracy@50
- cosine_accuracy@100
- cosine_accuracy@150
- cosine_accuracy@200
- cosine_precision@1
- cosine_precision@20
- cosine_precision@50
- cosine_precision@100
- cosine_precision@150
- cosine_precision@200
- cosine_recall@1
- cosine_recall@20
- cosine_recall@50
- cosine_recall@100
- cosine_recall@150
- cosine_recall@200
- cosine_ndcg@1
- cosine_ndcg@20
- cosine_ndcg@50
- cosine_ndcg@100
- cosine_ndcg@150
- cosine_ndcg@200
- cosine_mrr@1
- cosine_mrr@20
- cosine_mrr@50
- cosine_mrr@100
- cosine_mrr@150
- cosine_mrr@200
- cosine_map@1
- cosine_map@20
- cosine_map@50
- cosine_map@100
- cosine_map@150
- cosine_map@200
- cosine_map@500
model-index:
- name: SentenceTransformer based on BAAI/bge-large-en-v1.5
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full en
type: full_en
metrics:
- type: cosine_accuracy@1
value: 0.7302631578947368
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.993421052631579
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9967105263157895
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 1.0
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 1.0
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 1.0
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.7302631578947368
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.4998355263157894
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.39184210526315794
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.3111842105263158
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.2652412280701754
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.232171052631579
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.010227350724729817
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.13368254620254577
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.2541249933594102
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.3948435268881245
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.49626849018850344
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.5720837677245543
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.7302631578947368
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.5384654647855256
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.44986527953229877
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.44277699637488865
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.4895063673734854
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.5346148440105628
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.7302631578947368
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.8341772399749373
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.8343338815789473
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.8343905966424682
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.8343905966424682
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.8343905966424682
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.7302631578947368
name: Cosine Map@1
- type: cosine_map@20
value: 0.3434603918412553
name: Cosine Map@20
- type: cosine_map@50
value: 0.23779270403918282
name: Cosine Map@50
- type: cosine_map@100
value: 0.21161540263537876
name: Cosine Map@100
- type: cosine_map@150
value: 0.22899252179487295
name: Cosine Map@150
- type: cosine_map@200
value: 0.24784282323083537
name: Cosine Map@200
- type: cosine_map@500
value: 0.298154972004029
name: Cosine Map@500
---
# Job-Skill matching fintuned BAAI/bge-large-en-v1.5
Top performing model on [TalentCLEF 2025](https://talentclef.github.io/talentclef/) Task B. Use it for job title <-> skill set matching
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 256, 'do_lower_case': True}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("pj-mathematician/JobSkillBGE-large-en-v1.5")
# Run inference
sentences = [
'For roles such as import/export manager, graduate export manager, senior export manager, and other related positions in meat and meat products, the key skills include a strong understanding of international trade regulations, meat product knowledge, customs compliance, and excellent negotiation and communication skills to manage global supply chains effectively. Additionally, proficiency in relevant trade software and languages can be highly beneficial.',
'Job roles such as Performance Analyst, Quality Assurance Engineer, and Test Manager require skills in conducting performance measurement and organizing or managing conversion testing to ensure software and systems meet performance standards and function correctly in real-world scenarios.',
'Job roles that require skills such as managing staff, coordinating employees, and performing HR activities include Human Resources Managers, Team Leaders, Supervisors, and Department Heads, all of whom are responsible for overseeing personnel, implementing HR policies, and ensuring efficient team operations.',
]
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]
```
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `full_en`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:---------------------|:-----------|
| cosine_accuracy@1 | 0.7303 |
| cosine_accuracy@20 | 0.9934 |
| cosine_accuracy@50 | 0.9967 |
| cosine_accuracy@100 | 1.0 |
| cosine_accuracy@150 | 1.0 |
| cosine_accuracy@200 | 1.0 |
| cosine_precision@1 | 0.7303 |
| cosine_precision@20 | 0.4998 |
| cosine_precision@50 | 0.3918 |
| cosine_precision@100 | 0.3112 |
| cosine_precision@150 | 0.2652 |
| cosine_precision@200 | 0.2322 |
| cosine_recall@1 | 0.0102 |
| cosine_recall@20 | 0.1337 |
| cosine_recall@50 | 0.2541 |
| cosine_recall@100 | 0.3948 |
| cosine_recall@150 | 0.4963 |
| cosine_recall@200 | 0.5721 |
| cosine_ndcg@1 | 0.7303 |
| cosine_ndcg@20 | 0.5385 |
| cosine_ndcg@50 | 0.4499 |
| cosine_ndcg@100 | 0.4428 |
| cosine_ndcg@150 | 0.4895 |
| **cosine_ndcg@200** | **0.5346** |
| cosine_mrr@1 | 0.7303 |
| cosine_mrr@20 | 0.8342 |
| cosine_mrr@50 | 0.8343 |
| cosine_mrr@100 | 0.8344 |
| cosine_mrr@150 | 0.8344 |
| cosine_mrr@200 | 0.8344 |
| cosine_map@1 | 0.7303 |
| cosine_map@20 | 0.3435 |
| cosine_map@50 | 0.2378 |
| cosine_map@100 | 0.2116 |
| cosine_map@150 | 0.229 |
| cosine_map@200 | 0.2478 |
| cosine_map@500 | 0.2982 |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 114,699 training samples
* Columns: anchor and positive
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 43 tokens
- mean: 65.45 tokens
- max: 116 tokens
| - min: 34 tokens
- mean: 55.34 tokens
- max: 162 tokens
|
* Samples:
| anchor | positive |
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation. | Job roles that require promoting health and safety include occupational health and safety specialists, safety managers, and public health educators, all of whom work to ensure safe and healthy environments in workplaces and communities. |
| A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation. | Job roles that require organizing rehearsals include directors, choreographers, and conductors in theater, dance, and music ensembles, who must efficiently plan and schedule practice sessions to prepare performers for a successful final performance. |
| A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation. | Job roles such as Health and Safety Managers, Environmental Health Officers, and Risk Management Specialists often require the skill of negotiating health and safety issues with third parties to ensure compliance and protection standards are met across different organizations and sites. |
* Loss: [CachedGISTEmbedLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
```json
{'guide': SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: 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()
), 'temperature': 0.01, 'mini_batch_size': 32, 'margin_strategy': 'absolute', 'margin': 0.0}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 128
- `gradient_accumulation_steps`: 2
- `num_train_epochs`: 5
- `warmup_ratio`: 0.05
- `log_on_each_node`: False
- `fp16`: True
- `dataloader_num_workers`: 4
- `ddp_find_unused_parameters`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
Click to expand
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 128
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 2
- `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`: 5
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.05
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: False
- `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`: True
- `dataloader_num_workers`: 4
- `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}
- `tp_size`: 0
- `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`: True
- `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`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `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
- `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
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional