CrossEncoder based on distilbert/distilroberta-base

This is a Cross Encoder model finetuned from distilbert/distilroberta-base on the all-nli dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text pair classification.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: distilbert/distilroberta-base
• Maximum Sequence Length: 512 tokens
• Number of Output Labels: 3 labels
• Supported Modality: Text
• Training Dataset:
  • all-nli

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': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'RobertaForSequenceClassification'})
)

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("kwondw/reranker-distilroberta-base-nli")
# Get scores for pairs of inputs
pairs = [
    ['Two women are embracing while holding to go packages.', 'The sisters are hugging goodbye while holding to go packages after just eating lunch.'],
    ['Two women are embracing while holding to go packages.', 'Two woman are holding packages.'],
    ['Two women are embracing while holding to go packages.', 'The men are fighting outside a deli.'],
    ['Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.', 'Two kids in numbered jerseys wash their hands.'],
    ['Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.', 'Two kids at a ballgame wash their hands.'],
]
scores = model.predict(pairs)
print(scores)
# [[-2.6387  3.0625 -1.0605]
#  [ 3.3965 -0.6968 -1.874 ]
#  [-3.2012 -0.9272  3.6855]
#  [ 2.3809 -1.0547 -0.6987]
#  [-2.1973  1.748   0.0408]]

Evaluation

Metrics

Cross Encoder Classification

• Datasets: ALLNLI-dev and AllNLI-test
• Evaluated with CrossEncoderClassificationEvaluator

Training Details

Training Dataset

all-nli

• Dataset: all-nli
• Size: 100,000 training samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 100 samples:

  	premise	hypothesis	label
  type	string	string	int
  modality	text	text
  details	min: 8 tokensmean: 23.12 tokensmax: 45 tokens	min: 6 tokensmean: 11.24 tokensmax: 25 tokens	0: ~32.69%1: ~34.62%2: ~32.69%

• Samples:

  premise	hypothesis	label
  A person on a horse jumps over a broken down airplane.	A person is training his horse for a competition.	1
  A person on a horse jumps over a broken down airplane.	A person is at a diner, ordering an omelette.	2
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	0

• Loss: CrossEntropyLoss

Evaluation Dataset

all-nli

• Dataset: all-nli
• Size: 1,000 evaluation samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 100 samples:

  	premise	hypothesis	label
  type	string	string	int
  modality	text	text
  details	min: 9 tokensmean: 19.64 tokensmax: 36 tokens	min: 5 tokensmean: 10.2 tokensmax: 24 tokens	0: ~32.69%1: ~30.77%2: ~36.54%

• Samples:

  premise	hypothesis	label
  Two women are embracing while holding to go packages.	The sisters are hugging goodbye while holding to go packages after just eating lunch.	1
  Two women are embracing while holding to go packages.	Two woman are holding packages.	0
  Two women are embracing while holding to go packages.	The men are fighting outside a deli.	2

• Loss: CrossEntropyLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• num_train_epochs: 1
• warmup_steps: 0.1
• fp16: True
• ddp_find_unused_parameters: False

All Hyperparameters

• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• gradient_accumulation_steps: 1
• 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: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: None
• warmup_steps: 0.1
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: True
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• ddp_find_unused_parameters: False
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 2.2 minutes
• Evaluation: 0.6 seconds
• Total: 2.2 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 6.0.1
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 5.0.0
• Tokenizers: 0.22.2

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",
}