| --- |
| tags: |
| - sentence-transformers |
| - cross-encoder |
| - reranker |
| - generated_from_trainer |
| - dataset_size:120000 |
| - loss:BinaryCrossEntropyLoss |
| base_model: cross-encoder/ms-marco-MiniLM-L6-v2 |
| pipeline_tag: text-ranking |
| library_name: sentence-transformers |
| --- |
| |
| # CrossEncoder based on cross-encoder/ms-marco-MiniLM-L6-v2 |
|
|
| This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search. |
|
|
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** Cross Encoder |
| - **Base model:** [cross-encoder/ms-marco-MiniLM-L6-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L6-v2) <!-- at revision c5ee24cb16019beea0893ab7796b1df96625c6b8 --> |
| - **Maximum Sequence Length:** 256 tokens |
| - **Number of Output Labels:** 1 label |
| - **Supported Modality:** Text |
| <!-- - **Training Dataset:** Unknown --> |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| CrossEncoder( |
| (0): Transformer({'transformer_task': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'BertForSequenceClassification'}) |
| ) |
| ``` |
|
|
| ## 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 CrossEncoder |
| |
| # Download from the 🤗 Hub |
| model = CrossEncoder("cross_encoder_model_id") |
| # Get scores for pairs of inputs |
| pairs = [ |
| ['Job Title: Customer Support Specialist. Required Seniority: Junior. Industry: FinTech. Must-Have Skills: Ticketing, Documentation, Root Cause Analysis, Communication. Nice-to-Have Skills: Troubleshooting. Job Description: We are hiring a Customer Support Specialist to support teams in FinTech.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', 'Candidate Role: Customer Support Specialist. Seniority Level: Senior. Years of Experience: 9. Industry Experience: Retail. Education: High School. Skills: Ticketing, Documentation, Communication, Root Cause Analysis, SLA, Escalations, Troubleshooting, Intercom. Professional Summary: Customer Support Specialist with 9 years of experience in Retail.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.'], |
| ['Job Title: Junior Accountant. Required Seniority: Senior. Industry: Travel. Must-Have Skills: Valuation, Forecasting, Variance Analysis, KPIs. Nice-to-Have Skills: Budgeting. Job Description: We are hiring a Junior Accountant to support teams in Travel.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', 'Candidate Role: Financial Analyst. Seniority Level: Junior. Years of Experience: 2. Industry Experience: E-commerce. Education: MBA. Skills: Variance Analysis, KPIs, Reporting, Budgeting, Accounting, Valuation. Professional Summary: Financial Analyst with 2 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.'], |
| ['Job Title: Sales Representative. Required Seniority: Senior. Industry: Cybersecurity. Must-Have Skills: Prospecting, Account Management, Pipeline Management, Closing. Nice-to-Have Skills: Negotiation. Job Description: We are hiring a Sales Representative to support teams in Cybersecurity.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', 'Candidate Role: Sales Representative. Seniority Level: Mid. Years of Experience: 6. Industry Experience: SaaS. Education: High School. Skills: CRM, Negotiation, Prospecting, Pipeline Management, Discovery Calls, Closing, Account Management, Lead Generation. Professional Summary: Sales Representative with 6 years of experience in SaaS.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.'], |
| ['Job Title: Sales Representative. Required Seniority: Mid. Industry: E-commerce. Must-Have Skills: Prospecting, Negotiation, Outbound Outreach. Nice-to-Have Skills: CRM. Job Description: We are hiring a Sales Representative to support teams in E-commerce.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', 'Candidate Role: Sales Representative. Seniority Level: Mid. Years of Experience: 5. Industry Experience: E-commerce. Education: High School. Skills: Outbound Outreach, Closing, Forecasting, Negotiation, Pipeline Management, Prospecting, Lead Generation. Professional Summary: Sales Representative with 5 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.'], |
| ['Job Title: Program Coordinator. Required Seniority: Senior. Industry: Retail. Must-Have Skills: Reporting, Risk Management, Process Improvement, Timeline Management, KPIs. Nice-to-Have Skills: Stakeholder Communication. Job Description: We are hiring a Program Coordinator to support teams in Retail.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', 'Candidate Role: Program Coordinator. Seniority Level: Senior. Years of Experience: 11. Industry Experience: FinTech. Education: BA. Skills: Risk Management, Project Planning, KPIs, Jira, Reporting, Timeline Management, Asana, Process Improvement. Professional Summary: Program Coordinator with 11 years of experience in FinTech.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.'], |
| ] |
| scores = model.predict(pairs) |
| print(scores) |
| # [-0.3621 4.0586 -0.2727 -0.2522 -0.4119] |
| |
| # Or rank different texts based on similarity to a single text |
| ranks = model.rank( |
| 'Job Title: Customer Support Specialist. Required Seniority: Junior. Industry: FinTech. Must-Have Skills: Ticketing, Documentation, Root Cause Analysis, Communication. Nice-to-Have Skills: Troubleshooting. Job Description: We are hiring a Customer Support Specialist to support teams in FinTech.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.', |
| [ |
| 'Candidate Role: Customer Support Specialist. Seniority Level: Senior. Years of Experience: 9. Industry Experience: Retail. Education: High School. Skills: Ticketing, Documentation, Communication, Root Cause Analysis, SLA, Escalations, Troubleshooting, Intercom. Professional Summary: Customer Support Specialist with 9 years of experience in Retail.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.', |
| 'Candidate Role: Financial Analyst. Seniority Level: Junior. Years of Experience: 2. Industry Experience: E-commerce. Education: MBA. Skills: Variance Analysis, KPIs, Reporting, Budgeting, Accounting, Valuation. Professional Summary: Financial Analyst with 2 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.', |
| 'Candidate Role: Sales Representative. Seniority Level: Mid. Years of Experience: 6. Industry Experience: SaaS. Education: High School. Skills: CRM, Negotiation, Prospecting, Pipeline Management, Discovery Calls, Closing, Account Management, Lead Generation. Professional Summary: Sales Representative with 6 years of experience in SaaS.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.', |
| 'Candidate Role: Sales Representative. Seniority Level: Mid. Years of Experience: 5. Industry Experience: E-commerce. Education: High School. Skills: Outbound Outreach, Closing, Forecasting, Negotiation, Pipeline Management, Prospecting, Lead Generation. Professional Summary: Sales Representative with 5 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.', |
| 'Candidate Role: Program Coordinator. Seniority Level: Senior. Years of Experience: 11. Industry Experience: FinTech. Education: BA. Skills: Risk Management, Project Planning, KPIs, Jira, Reporting, Timeline Management, Asana, Process Improvement. Professional Summary: Program Coordinator with 11 years of experience in FinTech.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.', |
| ] |
| ) |
| # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...] |
| ``` |
|
|
| <!-- |
| ### Direct Usage (Transformers) |
|
|
| <details><summary>Click to see the direct usage in Transformers</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Downstream Usage (Sentence Transformers) |
|
|
| You can finetune this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Out-of-Scope Use |
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| --> |
|
|
| <!-- |
| ## Bias, Risks and Limitations |
|
|
| *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
| --> |
|
|
| <!-- |
| ### Recommendations |
|
|
| *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
| --> |
|
|
| ## Training Details |
|
|
| ### Training Dataset |
|
|
| #### Unnamed Dataset |
|
|
| * Size: 120,000 training samples |
| * Columns: <code>job_text</code>, <code>resume_text</code>, and <code>label</code> |
| * Approximate statistics based on the first 100 samples: |
| | | job_text | resume_text | label | |
| |:---------|:--------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:---------------------------------------------------------------| |
| | type | string | string | float | |
| | modality | text | text | | |
| | details | <ul><li>min: 117 tokens</li><li>mean: 125.18 tokens</li><li>max: 136 tokens</li></ul> | <ul><li>min: 92 tokens</li><li>mean: 101.44 tokens</li><li>max: 112 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> | |
| * Samples: |
| | job_text | resume_text | label | |
| |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| |
| | <code>Job Title: Technical Support Specialist. Required Seniority: Junior. Industry: FinTech. Must-Have Skills: Escalations, SLA, Documentation, Communication, Intercom. Nice-to-Have Skills: Ticketing. Job Description: We are hiring a Technical Support Specialist to support teams in FinTech.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Customer Success Associate. Seniority Level: Mid. Years of Experience: 2. Industry Experience: E-commerce. Education: BA. Skills: Intercom, SLA, Customer Satisfaction, Documentation, Root Cause Analysis, Communication, Ticketing. Professional Summary: Customer Success Associate with 2 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>1.0</code> | |
| | <code>Job Title: FP&A Analyst. Required Seniority: Junior. Industry: Logistics. Must-Have Skills: Forecasting, KPIs, Reporting, Accounting. Nice-to-Have Skills: Financial Modeling. Job Description: We are hiring a FP&A Analyst to support teams in Logistics.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Financial Analyst. Seniority Level: Senior. Years of Experience: 7. Industry Experience: E-commerce. Education: High School. Skills: Excel, Accounting, Cash Flow, Reporting, Variance Analysis, Financial Modeling, Valuation, Forecasting. Professional Summary: Financial Analyst with 7 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>1.0</code> | |
| | <code>Job Title: Content Marketer. Required Seniority: Senior. Industry: Travel. Must-Have Skills: SEO, Copywriting, Meta Ads, Email Marketing, Google Ads. Nice-to-Have Skills: Content Marketing. Job Description: We are hiring a Content Marketer to support teams in Travel.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Content Marketer. Seniority Level: Junior. Years of Experience: 0. Industry Experience: Retail. Education: MSc. Skills: Copywriting, Conversion Optimization, Landing Pages, Content Marketing, Google Ads, Meta Ads, A/B Testing, SEO. Professional Summary: Content Marketer with 0 years of experience in Retail.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>0.0</code> | |
| * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters: |
| ```json |
| { |
| "activation_fn": "torch.nn.modules.linear.Identity", |
| "pos_weight": null |
| } |
| ``` |
|
|
| ### Evaluation Dataset |
|
|
| #### Unnamed Dataset |
|
|
| * Size: 15,000 evaluation samples |
| * Columns: <code>job_text</code>, <code>resume_text</code>, and <code>label</code> |
| * Approximate statistics based on the first 100 samples: |
| | | job_text | resume_text | label | |
| |:---------|:--------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------| |
| | type | string | string | float | |
| | modality | text | text | | |
| | details | <ul><li>min: 116 tokens</li><li>mean: 125.31 tokens</li><li>max: 134 tokens</li></ul> | <ul><li>min: 91 tokens</li><li>mean: 100.88 tokens</li><li>max: 111 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.4</li><li>max: 1.0</li></ul> | |
| * Samples: |
| | job_text | resume_text | label | |
| |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| |
| | <code>Job Title: Customer Support Specialist. Required Seniority: Junior. Industry: FinTech. Must-Have Skills: Ticketing, Documentation, Root Cause Analysis, Communication. Nice-to-Have Skills: Troubleshooting. Job Description: We are hiring a Customer Support Specialist to support teams in FinTech.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Customer Support Specialist. Seniority Level: Senior. Years of Experience: 9. Industry Experience: Retail. Education: High School. Skills: Ticketing, Documentation, Communication, Root Cause Analysis, SLA, Escalations, Troubleshooting, Intercom. Professional Summary: Customer Support Specialist with 9 years of experience in Retail.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>0.0</code> | |
| | <code>Job Title: Junior Accountant. Required Seniority: Senior. Industry: Travel. Must-Have Skills: Valuation, Forecasting, Variance Analysis, KPIs. Nice-to-Have Skills: Budgeting. Job Description: We are hiring a Junior Accountant to support teams in Travel.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Financial Analyst. Seniority Level: Junior. Years of Experience: 2. Industry Experience: E-commerce. Education: MBA. Skills: Variance Analysis, KPIs, Reporting, Budgeting, Accounting, Valuation. Professional Summary: Financial Analyst with 2 years of experience in E-commerce.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>1.0</code> | |
| | <code>Job Title: Sales Representative. Required Seniority: Senior. Industry: Cybersecurity. Must-Have Skills: Prospecting, Account Management, Pipeline Management, Closing. Nice-to-Have Skills: Negotiation. Job Description: We are hiring a Sales Representative to support teams in Cybersecurity.. Responsibilities: Deliver high-quality work aligned with goals and timelines; Collaborate with stakeholders and communicate progress clearly; Improve processes and contribute to measurable outcomes. Requirements: Relevant experience and ability to learn quickly; Strong communication and ownership mindset; Comfort working with tools, data, and cross-functional teams.</code> | <code>Candidate Role: Sales Representative. Seniority Level: Mid. Years of Experience: 6. Industry Experience: SaaS. Education: High School. Skills: CRM, Negotiation, Prospecting, Pipeline Management, Discovery Calls, Closing, Account Management, Lead Generation. Professional Summary: Sales Representative with 6 years of experience in SaaS.. Experience Highlights: Delivered results using structured workflows and clear communication; Collaborated with stakeholders to define needs and execute tasks; Maintained reporting and documentation to support team performance.</code> | <code>0.0</code> | |
| * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters: |
| ```json |
| { |
| "activation_fn": "torch.nn.modules.linear.Identity", |
| "pos_weight": null |
| } |
| ``` |
|
|
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
|
|
| - `per_device_train_batch_size`: 32 |
| - `num_train_epochs`: 2 |
| - `learning_rate`: 2e-05 |
| - `warmup_steps`: 0.1 |
| - `weight_decay`: 0.01 |
| - `fp16`: True |
| - `auto_find_batch_size`: True |
| - `per_device_eval_batch_size`: 32 |
| - `eval_accumulation_steps`: 4 |
| - `load_best_model_at_end`: True |
| - `data_seed`: 42 |
| - `dataloader_num_workers`: 2 |
| - `dataloader_persistent_workers`: True |
|
|
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
|
|
| - `per_device_train_batch_size`: 32 |
| - `num_train_epochs`: 2 |
| - `max_steps`: -1 |
| - `learning_rate`: 2e-05 |
| - `lr_scheduler_type`: linear |
| - `lr_scheduler_kwargs`: None |
| - `warmup_steps`: 0.1 |
| - `optim`: adamw_torch_fused |
| - `optim_args`: None |
| - `weight_decay`: 0.01 |
| - `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`: 1.0 |
| - `label_smoothing_factor`: 0.0 |
| - `bf16`: False |
| - `fp16`: True |
| - `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`: True |
| - `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`: 32 |
| - `prediction_loss_only`: True |
| - `eval_on_start`: False |
| - `eval_do_concat_batches`: True |
| - `eval_use_gather_object`: False |
| - `eval_accumulation_steps`: 4 |
| - `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`: True |
| - `ignore_data_skip`: False |
| - `restore_callback_states_from_checkpoint`: False |
| - `full_determinism`: False |
| - `seed`: 42 |
| - `data_seed`: 42 |
| - `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`: 2 |
| - `dataloader_pin_memory`: True |
| - `dataloader_persistent_workers`: True |
| - `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`: proportional |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
|
|
| </details> |
|
|
| ### Training Logs |
| | Epoch | Step | Training Loss | Validation Loss | |
| |:-------:|:--------:|:-------------:|:---------------:| |
| | 0.0003 | 1 | 1.1285 | - | |
| | 0.0267 | 100 | 0.9878 | - | |
| | 0.0533 | 200 | 0.7241 | - | |
| | 0.08 | 300 | 0.6373 | - | |
| | 0.1067 | 400 | 0.5818 | - | |
| | 0.1333 | 500 | 0.5057 | - | |
| | 0.16 | 600 | 0.4458 | - | |
| | 0.1867 | 700 | 0.4322 | - | |
| | 0.2133 | 800 | 0.3922 | - | |
| | 0.24 | 900 | 0.3820 | - | |
| | 0.2667 | 1000 | 0.3756 | 0.3510 | |
| | 0.2933 | 1100 | 0.3824 | - | |
| | 0.32 | 1200 | 0.3423 | - | |
| | 0.3467 | 1300 | 0.3432 | - | |
| | 0.3733 | 1400 | 0.3643 | - | |
| | 0.4 | 1500 | 0.3589 | - | |
| | 0.4267 | 1600 | 0.3619 | - | |
| | 0.4533 | 1700 | 0.3572 | - | |
| | 0.48 | 1800 | 0.3604 | - | |
| | 0.5067 | 1900 | 0.3362 | - | |
| | 0.5333 | 2000 | 0.3453 | 0.3266 | |
| | 0.56 | 2100 | 0.3397 | - | |
| | 0.5867 | 2200 | 0.3627 | - | |
| | 0.6133 | 2300 | 0.3620 | - | |
| | 0.64 | 2400 | 0.3257 | - | |
| | 0.6667 | 2500 | 0.3533 | - | |
| | 0.6933 | 2600 | 0.3408 | - | |
| | 0.72 | 2700 | 0.3269 | - | |
| | 0.7467 | 2800 | 0.3446 | - | |
| | 0.7733 | 2900 | 0.3380 | - | |
| | 0.8 | 3000 | 0.3529 | 0.3219 | |
| | 0.8267 | 3100 | 0.3423 | - | |
| | 0.8533 | 3200 | 0.3213 | - | |
| | 0.88 | 3300 | 0.3529 | - | |
| | 0.9067 | 3400 | 0.3523 | - | |
| | 0.9333 | 3500 | 0.3403 | - | |
| | 0.96 | 3600 | 0.3344 | - | |
| | 0.9867 | 3700 | 0.3503 | - | |
| | 1.0133 | 3800 | 0.3468 | - | |
| | 1.04 | 3900 | 0.3213 | - | |
| | 1.0667 | 4000 | 0.3421 | 0.3219 | |
| | 1.0933 | 4100 | 0.3465 | - | |
| | 1.12 | 4200 | 0.3227 | - | |
| | 1.1467 | 4300 | 0.3392 | - | |
| | 1.1733 | 4400 | 0.3268 | - | |
| | 1.2 | 4500 | 0.3257 | - | |
| | 1.2267 | 4600 | 0.3328 | - | |
| | 1.2533 | 4700 | 0.3453 | - | |
| | 1.28 | 4800 | 0.3377 | - | |
| | 1.3067 | 4900 | 0.3268 | - | |
| | 1.3333 | 5000 | 0.3402 | 0.3160 | |
| | 1.3600 | 5100 | 0.3420 | - | |
| | 1.3867 | 5200 | 0.3129 | - | |
| | 1.4133 | 5300 | 0.3434 | - | |
| | 1.44 | 5400 | 0.3416 | - | |
| | 1.4667 | 5500 | 0.3468 | - | |
| | 1.4933 | 5600 | 0.3231 | - | |
| | 1.52 | 5700 | 0.3163 | - | |
| | 1.5467 | 5800 | 0.3165 | - | |
| | 1.5733 | 5900 | 0.3356 | - | |
| | 1.6 | 6000 | 0.3245 | 0.3128 | |
| | 1.6267 | 6100 | 0.3204 | - | |
| | 1.6533 | 6200 | 0.3091 | - | |
| | 1.6800 | 6300 | 0.3355 | - | |
| | 1.7067 | 6400 | 0.3318 | - | |
| | 1.7333 | 6500 | 0.3407 | - | |
| | 1.76 | 6600 | 0.3303 | - | |
| | 1.7867 | 6700 | 0.3145 | - | |
| | 1.8133 | 6800 | 0.3388 | - | |
| | 1.8400 | 6900 | 0.3334 | - | |
| | 1.8667 | 7000 | 0.3249 | 0.3131 | |
| | 1.8933 | 7100 | 0.3379 | - | |
| | 1.92 | 7200 | 0.3195 | - | |
| | 1.9467 | 7300 | 0.3294 | - | |
| | 1.9733 | 7400 | 0.3312 | - | |
| | **2.0** | **7500** | **0.3255** | **0.3127** | |
|
|
| * The bold row denotes the saved checkpoint. |
|
|
| ### Training Time |
| - **Training**: 9.4 minutes |
|
|
| ### Framework Versions |
| - Python: 3.12.13 |
| - Sentence Transformers: 5.6.0 |
| - Transformers: 5.13.1 |
| - PyTorch: 2.11.0+cu128 |
| - Accelerate: 1.14.0 |
| - Datasets: 4.0.0 |
| - Tokenizers: 0.22.2 |
|
|
| ## Additional Resources |
|
|
| - [Training and Finetuning Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-reranker): the end-to-end guide for training or finetuning Cross Encoder (reranker) models. |
| - [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video reranker models through the same API. |
| - [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): training multimodal Cross Encoders. |
|
|
| ## Citation |
|
|
| ### BibTeX |
|
|
| #### Sentence Transformers |
| ```bibtex |
| @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", |
| } |
| ``` |
|
|
| <!-- |
| ## Glossary |
|
|
| *Clearly define terms in order to be accessible across audiences.* |
| --> |
|
|
| <!-- |
| ## Model Card Authors |
|
|
| *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
| --> |
|
|
| <!-- |
| ## Model Card Contact |
|
|
| *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
| --> |
