tomaarsen/reranker-distilroberta-base-nli

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 semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Cross Encoder
• Base model: distilbert/distilroberta-base
• Maximum Sequence Length: 514 tokens
• Training Dataset:
  • all-nli
• Language: en

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("tomaarsen/reranker-distilroberta-base-nli")
# Get scores for pairs...
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.shape)
# [5]

# ... or rank different texts based on similarity to a single text
ranks = model.rank(
    'Two women are embracing while holding to go packages.',
    [
        'The sisters are hugging goodbye while holding to go packages after just eating lunch.',
        'Two woman are holding packages.',
        'The men are fighting outside a deli.',
        'Two kids in numbered jerseys wash their hands.',
        'Two kids at a ballgame wash their hands.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Classification

• Datasets: AllNLI-dev and AllNLI-test
• Evaluated with CEClassificationEvaluator

Metric	AllNLI-dev	AllNLI-test
f1_macro	0.8495	0.7574
f1_micro	0.851	0.7576
f1_weighted	0.8495	0.7583

Training Details

Training Dataset

all-nli

• Dataset: all-nli at d482672
• Size: 942,069 training samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 23 characters mean: 69.54 characters max: 227 characters	min: 11 characters mean: 38.26 characters max: 131 characters	0: ~33.40% 1: ~33.30% 2: ~33.30%

• 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 at d482672
• Size: 19,657 evaluation samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 16 characters mean: 75.01 characters max: 229 characters	min: 11 characters mean: 37.66 characters max: 116 characters	0: ~33.10% 1: ~33.30% 2: ~33.60%

• 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

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True

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: 64
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• 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: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• 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: True
• fp16: False
• 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: False
• dataloader_num_workers: 0
• 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}
• 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: None
• 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
• dispatch_batches: None
• split_batches: 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: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	AllNLI-dev_f1_macro	AllNLI-test_f1_macro
-1	-1	-	-	0.1677	-
0.0640	100	1.0454	-	-	-
0.1280	200	0.7193	-	-	-
0.1919	300	0.6247	-	-	-
0.2559	400	0.5907	-	-	-
0.3199	500	0.5671	0.4578	0.8206	-
0.3839	600	0.5384	-	-	-
0.4479	700	0.5492	-	-	-
0.5118	800	0.5281	-	-	-
0.5758	900	0.5043	-	-	-
0.6398	1000	0.5243	0.4012	0.8415	-
0.7038	1100	0.4906	-	-	-
0.7678	1200	0.4877	-	-	-
0.8317	1300	0.4506	-	-	-
0.8957	1400	0.4728	-	-	-
0.9597	1500	0.4602	0.3731	0.8495	-
-1	-1	-	-	-	0.7574

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 0.015 kWh
• Carbon Emitted: 0.006 kg of CO2
• Hours Used: 0.058 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 3.5.0.dev0
• Transformers: 4.49.0.dev0
• PyTorch: 2.5.0+cu121
• Accelerate: 1.3.0
• Datasets: 2.20.0
• Tokenizers: 0.21.0

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",
}