reranker-ModernBERT-base-gooaq-bce-50k

MordernBERT-base trained on GooAQ

This is a Cross Encoder model finetuned from answerdotai/ModernBERT-base 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: answerdotai/ModernBERT-base <!-- at revision 8949b909ec900327062f0ebf497f51aef5e6f0c8 -->
• Maximum Sequence Length: 8192 tokens
• Number of Output Labels: 1 label
• Supported Modality: Text

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

• Language: en
• License: apache-2.0

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': 'ModernBertForSequenceClassification'})
)

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-ModernBERT-base-gooaq-bce-50k")
# Get scores for pairs of inputs
pairs = [
    ['is corpse bride on hulu?', ". Watch Corpse Bride on Hulu either streaming online or on your favorite device. It's easy to watch Corpse Bride streaming online if you have either the Hulu basic or the Hulu Premium. ... HBO Max now has Corpse Bride streaming with a subscription."],
    ['is corpse bride on hulu?', 'When you put your day-of timeline together, try to keep these guidelines in mind: Makeup: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride. Hair: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride.'],
    ['is corpse bride on hulu?', "A dowry is a transfer of parental property, gifts, or money at the marriage of a daughter (bride). ... While bride price or bride service is a payment by the groom or his family to the bride's parents, dowry is the wealth transferred from the bride's family to the groom or his family, ostensibly for the bride."],
    ['is corpse bride on hulu?', 'The traditional wedding speech order goes father of the bride, groom, best man and other toasts. However, lots of brides now choose to give a speech, as do the bridesmaids or maid of honour. If you are including these, the order should go: father of the bride, groom, bride, bridesmaids/maid of honour, best man.'],
    ['is corpse bride on hulu?', "If the bride can afford to, it's a very thoughtful gesture for her to pay for the dress or a portion of the cost for each of her bridesmaids. ... Generally speaking, bridesmaids are expected to pay for their own dresses and accessories, as well as potentially hair and makeup appointments and transportation to the wedding."],
]
scores = model.predict(pairs)
print(scores)
# [9.9504e-01 4.7737e-03 1.2148e-04 1.8603e-03 2.1824e-04]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'is corpse bride on hulu?',
    [
        ". Watch Corpse Bride on Hulu either streaming online or on your favorite device. It's easy to watch Corpse Bride streaming online if you have either the Hulu basic or the Hulu Premium. ... HBO Max now has Corpse Bride streaming with a subscription.",
        'When you put your day-of timeline together, try to keep these guidelines in mind: Makeup: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride. Hair: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride.',
        "A dowry is a transfer of parental property, gifts, or money at the marriage of a daughter (bride). ... While bride price or bride service is a payment by the groom or his family to the bride's parents, dowry is the wealth transferred from the bride's family to the groom or his family, ostensibly for the bride.",
        'The traditional wedding speech order goes father of the bride, groom, best man and other toasts. However, lots of brides now choose to give a speech, as do the bridesmaids or maid of honour. If you are including these, the order should go: father of the bride, groom, bride, bridesmaids/maid of honour, best man.',
        "If the bride can afford to, it's a very thoughtful gesture for her to pay for the dress or a portion of the cost for each of her bridesmaids. ... Generally speaking, bridesmaids are expected to pay for their own dresses and accessories, as well as potentially hair and makeup appointments and transportation to the wedding.",
    ]
)
# [{'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 Reranking

• Dataset: gooaq-dev
• Evaluated with <code>CrossEncoderRerankingEvaluator</code> with these parameters:

  {
      "at_k": 10,
      "always_rerank_positives": false
  }
  

Cross Encoder Reranking

• Datasets: NanoMSMARCO_R100, NanoNFCorpus_R100 and NanoNQ_R100
• Evaluated with <code>CrossEncoderRerankingEvaluator</code> with these parameters:

  {
      "at_k": 10,
      "always_rerank_positives": true
  }
  

Cross Encoder Nano BEIR

• Dataset: NanoBEIR_R100_mean
• Evaluated with <code>CrossEncoderNanoBEIREvaluator</code> with these parameters:

  {
      "dataset_names": [
          "msmarco",
          "nfcorpus",
          "nq"
      ],
      "dataset_id": "sentence-transformers/NanoBEIR-en",
      "rerank_k": 100,
      "at_k": 10,
      "always_rerank_positives": true
  }
  

<!-- ## 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: 2,758,533 training samples
• Columns: <code>question</code>, <code>answer</code>, and <code>label</code>
• Approximate statistics based on the first 100 samples:

  	question	answer	label
  type	string	string	int
  modality	text	text
  details	<ul><li>min: 9 tokens</li><li>mean: 12.59 tokens</li><li>max: 18 tokens</li></ul>	<ul><li>min: 18 tokens</li><li>mean: 58.07 tokens</li><li>max: 135 tokens</li></ul>	<ul><li>0: ~81.73%</li><li>1: ~18.27%</li></ul>

• Samples:

  question	answer	label
  <code>is corpse bride on hulu?</code>	<code>. Watch Corpse Bride on Hulu either streaming online or on your favorite device. It's easy to watch Corpse Bride streaming online if you have either the Hulu basic or the Hulu Premium. ... HBO Max now has Corpse Bride streaming with a subscription.</code>	<code>1</code>
  <code>is corpse bride on hulu?</code>	<code>When you put your day-of timeline together, try to keep these guidelines in mind: Makeup: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride. Hair: 30–45 minutes per bridesmaid and mother of the bride, 60–90 minutes for the bride.</code>	<code>0</code>
  <code>is corpse bride on hulu?</code>	<code>A dowry is a transfer of parental property, gifts, or money at the marriage of a daughter (bride). ... While bride price or bride service is a payment by the groom or his family to the bride's parents, dowry is the wealth transferred from the bride's family to the groom or his family, ostensibly for the bride.</code>	<code>0</code>

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

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": 5
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_steps: 0.1
• seed: 12
• fp16: True
• dataloader_num_workers: 2
• load_best_model_at_end: True
• ddp_find_unused_parameters: False
• dataloader_persistent_workers: True

All Hyperparameters

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

• 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: 2e-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: 12
• 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: 2
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: True
• 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: True
• 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: {}

</details>

Training Logs

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

• The bold row denotes the saved checkpoint.

</details>

Training Time

• Training: 3.8 hours
• Evaluation: 26.3 minutes
• Total: 4.2 hours

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",
}

<!-- ## 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.* -->