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
Maximum Sequence Length: 128 tokens
Number of Output Labels: 1 label
Supported Modality: Text

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': ...}, ...]

Evaluation

Metrics

Cross Encoder Correlation

Dataset: val_correlation
Evaluated with CrossEncoderCorrelationEvaluator

Metric	Value
pearson	0.8442
spearman	0.8962

Training Details

Training Dataset

Unnamed Dataset

Size: 295,091 training samples
Columns: sentence1, sentence2, and label

Approximate statistics based on the first 100 samples:

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

Samples:

sentence1	sentence2	label
`Monitor customer preferences to determine focus of sales efforts.`	`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.`	`0.07737485777805486`
`Collaborate with colleagues to address teaching and research issues.`	`Collaborate with colleagues to address teaching and research issues.`	`0.6937963999029872`
`Keep abreast of developments in the field by reading current literature, talking with colleagues, and participating in professional conferences.`	`Keep abreast of developments in the field by reading current literature, talking with colleagues, and participating in professional conferences.`	`0.6937963999029872`

Loss: BinaryCrossEntropyLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 32,788 evaluation samples
Columns: sentence1, sentence2, and label

Approximate statistics based on the first 100 samples:

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

Samples:

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

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

All Hyperparameters

Click to expand

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

Training Logs

Epoch	Step	Training Loss	Validation Loss	val_correlation_spearman
0.0434	100	1.6617	-	-
0.0867	200	0.4783	-	-
0.1301	300	0.4244	-	-
0.1735	400	0.4227	-	-
0.2168	500	0.4231	-	-
0.2602	600	0.4164	-	-
0.3036	700	0.4201	-	-
0.3469	800	0.4195	-	-
0.3903	900	0.4109	-	-
0.4337	1000	0.4132	-	-
0.4770	1100	0.4145	-	-
0.5204	1200	0.4169	-	-
0.5637	1300	0.4135	-	-
0.6071	1400	0.4179	-	-
0.6505	1500	0.4085	-	-
0.6938	1600	0.4119	-	-
0.7372	1700	0.4125	-	-
0.7806	1800	0.4119	-	-
0.8239	1900	0.4096	-	-
0.8673	2000	0.4123	-	-
0.9107	2100	0.4081	-	-
0.9540	2200	0.4084	-	-
0.9974	2300	0.4100	-	-
1.0	2306	-	0.4095	0.8917
1.0408	2400	0.4077	-	-
1.0841	2500	0.4046	-	-
1.1275	2600	0.4061	-	-
1.1709	2700	0.4052	-	-
1.2142	2800	0.4055	-	-
1.2576	2900	0.4062	-	-
1.3010	3000	0.4026	-	-
1.3443	3100	0.4059	-	-
1.3877	3200	0.4039	-	-
1.4310	3300	0.4050	-	-
1.4744	3400	0.4047	-	-
1.5178	3500	0.4004	-	-
1.5611	3600	0.4053	-	-
1.6045	3700	0.4008	-	-
1.6479	3800	0.4042	-	-
1.6912	3900	0.4015	-	-
1.7346	4000	0.4057	-	-
1.7780	4100	0.4018	-	-
1.8213	4200	0.4048	-	-
1.8647	4300	0.4015	-	-
1.9081	4400	0.4052	-	-
1.9514	4500	0.4026	-	-
1.9948	4600	0.4028	-	-
2.0	4612	-	0.4062	0.8967
2.0382	4700	0.3993	-	-
2.0815	4800	0.3973	-	-
2.1249	4900	0.3982	-	-
2.1683	5000	0.3991	-	-
2.2116	5100	0.3956	-	-
2.2550	5200	0.4006	-	-
2.2984	5300	0.3985	-	-
2.3417	5400	0.3962	-	-
2.3851	5500	0.3964	-	-
2.4284	5600	0.4017	-	-
2.4718	5700	0.3977	-	-
2.5152	5800	0.3981	-	-
2.5585	5900	0.3968	-	-
2.6019	6000	0.3973	-	-
2.6453	6100	0.3993	-	-
2.6886	6200	0.4029	-	-
2.7320	6300	0.4011	-	-
2.7754	6400	0.3980	-	-
2.8187	6500	0.3955	-	-
2.8621	6600	0.3985	-	-
2.9055	6700	0.3952	-	-
2.9488	6800	0.3948	-	-
2.9922	6900	0.3972	-	-
3.0	6918	-	0.4057	0.8962

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",
}