zkarbie/context-lattice-semantic-reranker

CrossEncoder based on cross-encoder/ms-marco-MiniLM-L6-v2

This is a Cross Encoder model finetuned from cross-encoder/ms-marco-MiniLM-L6-v2 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/ms-marco-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Number of Output Labels: 1 label

Model Sources

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

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 texts
pairs = [
    ['How to implement error handling', 'Implementation guide for error handling. Step-by-step instructions with code examples. Covers setup, configuration, and best practices.'],
    ['Where is UserModel defined', 'Source code location and module structure. Class definitions and interface documentation. File paths and import statements.'],
    ['Add metrics collection to scheduler', 'Feature implementation guide with API extensions. Configuration options and customization points. Testing requirements.'],
    ['Fix bug in data processor', 'Company holiday schedule and PTO policy. HR contact information.'],
    ['Refactor authentication middleware for better readability', 'Refactoring patterns and code improvement strategies. Before/after examples with measurable improvements. Migration guide.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'How to implement error handling',
    [
        'Implementation guide for error handling. Step-by-step instructions with code examples. Covers setup, configuration, and best practices.',
        'Source code location and module structure. Class definitions and interface documentation. File paths and import statements.',
        'Feature implementation guide with API extensions. Configuration options and customization points. Testing requirements.',
        'Company holiday schedule and PTO policy. HR contact information.',
        'Refactoring patterns and code improvement strategies. Before/after examples with measurable improvements. Migration guide.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Correlation

• Dataset: val
• Evaluated with CECorrelationEvaluator

Metric	Value
pearson	0.9929
spearman	0.9384

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,600 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 20 characters mean: 32.95 characters max: 61 characters	min: 48 characters mean: 110.73 characters max: 158 characters	min: 0.0 mean: 0.56 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  How to implement error handling	Implementation guide for error handling. Step-by-step instructions with code examples. Covers setup, configuration, and best practices.	1.0
  Where is UserModel defined	Source code location and module structure. Class definitions and interface documentation. File paths and import statements.	1.0
  Add metrics collection to scheduler	Feature implementation guide with API extensions. Configuration options and customization points. Testing requirements.	1.0

• Loss: BinaryCrossEntropyLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• eval_strategy: steps
• per_device_eval_batch_size: 16

All Hyperparameters

Click to expand

• per_device_train_batch_size: 16
• 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: steps
• 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_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: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	val_spearman
1.0	100	0.9382
2.0	200	0.9384
3.0	300	0.9384

Framework Versions

• Python: 3.13.5
• Sentence Transformers: 5.3.0
• Transformers: 5.5.0
• PyTorch: 2.11.0+cu130
• Accelerate: 1.13.0
• Datasets: 4.8.4
• 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",
}