task-cross-encoder-v1

CrossEncoder based on cross-encoder/ettin-reranker-68m-v1

This is a Cross Encoder model finetuned from cross-encoder/ettin-reranker-68m-v1 using the sentence-transformers 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/ettin-reranker-68m-v1 <!-- at revision d166fa88ddde3c42bc3ee92f7df476d941c8204a -->
• Maximum Sequence Length: 128 tokens
• Number of Output Labels: 1 label
• Supported Modality: Text

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

Full Model Architecture

CrossEncoder(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'ModernBertModel'})
  (1): Pooling({'embedding_dimension': 512, 'pooling_mode': 'cls', 'include_prompt': True})
  (2): Dense({'in_features': 512, 'out_features': 512, 'bias': False, 'activation_function': 'torch.nn.modules.activation.GELU', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
  (3): LayerNorm({'dimension': 512})
  (4): Dense({'in_features': 512, 'out_features': 1, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'scores'})
)

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("cross_encoder_model_id")
# Get scores for pairs of inputs
pairs = [
    ['Plan, organize, or maintain dental health programs.', 'Turn or reposition bedridden patients.'],
    ['Maintain required records of work hours, budgets, payrolls, and other information.', 'Process payroll information.'],
    ['Conduct research to develop or test medications, treatments, or procedures to prevent or control disease or injury.', 'Conduct clinical or basic research.'],
    ['Prepare and submit reports describing the results of security fixes.', 'Receive patients, schedule appointments, and maintain patient records.'],
    ['Determine work assignments and procedures.', 'Conduct inventories to maintain stock of clinical supplies.'],
]
scores = model.predict(pairs)
print(scores)
# [-2.6881  1.3212 -0.5072 -2.6118 -2.2695]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'Plan, organize, or maintain dental health programs.',
    [
        'Turn or reposition bedridden patients.',
        'Process payroll information.',
        'Conduct clinical or basic research.',
        'Receive patients, schedule appointments, and maintain patient records.',
        'Conduct inventories to maintain stock of clinical supplies.',
    ]
)
# [{'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.* -->

Evaluation

Metrics

Cross Encoder Correlation

• Dataset: val_correlation
• Evaluated with <code>CrossEncoderCorrelationEvaluator</code>

<!-- ## 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: 295,091 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	sentence1	sentence2	label
  type	string	string	float
  modality	text	text
  details	<ul><li>min: 5 tokens</li><li>mean: 17.71 tokens</li><li>max: 46 tokens</li></ul>	<ul><li>min: 8 tokens</li><li>mean: 17.44 tokens</li><li>max: 40 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.28</li><li>max: 0.78</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>Monitor customer preferences to determine focus of sales efforts.</code>	<code>Advise food service managers and organizations on sanitation, safety procedures, menu development, budgeting, and planning to assist with establishment, operation, and evaluation of food service facilities and nutrition programs.</code>	<code>0.07737485777805486</code>
  <code>Collaborate with colleagues to address teaching and research issues.</code>	<code>Collaborate with colleagues to address teaching and research issues.</code>	<code>0.6937963999029872</code>
  <code>Keep abreast of developments in the field by reading current literature, talking with colleagues, and participating in professional conferences.</code>	<code>Keep abreast of developments in the field by reading current literature, talking with colleagues, and participating in professional conferences.</code>	<code>0.6937963999029872</code>

• Loss: <code>BinaryCrossEntropyLoss</code> with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 32,788 evaluation samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	sentence1	sentence2	label
  type	string	string	float
  modality	text	text
  details	<ul><li>min: 6 tokens</li><li>mean: 17.59 tokens</li><li>max: 45 tokens</li></ul>	<ul><li>min: 6 tokens</li><li>mean: 18.17 tokens</li><li>max: 55 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.28</li><li>max: 0.82</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>Plan, organize, or maintain dental health programs.</code>	<code>Turn or reposition bedridden patients.</code>	<code>0.056361597787474016</code>
  <code>Maintain required records of work hours, budgets, payrolls, and other information.</code>	<code>Process payroll information.</code>	<code>0.8059258707828006</code>
  <code>Conduct research to develop or test medications, treatments, or procedures to prevent or control disease or injury.</code>	<code>Conduct clinical or basic research.</code>	<code>0.37034095223637237</code>

• Loss: <code>BinaryCrossEntropyLoss</code> with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 128
• learning_rate: 2e-05
• warmup_steps: 0.1
• per_device_eval_batch_size: 128
• load_best_model_at_end: True

All Hyperparameters

<details><summary>Click to expand</summary>

• per_device_train_batch_size: 128
• num_train_epochs: 3
• 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: 0.0
• 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: 1.0
• 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: 128
• 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: True
• 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
• dataloader_multiprocessing_context: None
• dataloader_in_order: True
• 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
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}
• warmup_ratio: None

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Training Time

• Training: 1.4 hours

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 5.6.0
• Transformers: 5.16.1
• PyTorch: 2.13.0+cu130
• Accelerate: 1.14.0
• Datasets: 5.0.0
• Tokenizers: 0.23.2

Additional Resources

• Training and Finetuning Reranker Models with Sentence Transformers: the end-to-end guide for training or finetuning Cross Encoder (reranker) models.
• Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video reranker models through the same API.
• Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: training multimodal Cross Encoders.

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",
}

<!-- ## 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.* -->