reranker-ModernBERT-base-gooaq-bce-495000

ModernBERT-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

<!-- - **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

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("ayushexel/reranker-ModernBERT-base-gooaq-bce-495000")
# Get scores for pairs of texts
pairs = [
    ['how much coffee is in a mocha frappe from starbucks?', 'The Mocha Frappuccino Light Blended Beverage has slightly more caffeine: Tall - 60 mg. Grande - 95 mg. Venti Iced - 120 mg.'],
    ['how much coffee is in a mocha frappe from starbucks?', "Typically Starbucks Vanilla Bean Frappuccino has no coffee in it at all. I believe it's made with sweetened condensed milk, vanilla bean powder and ice and topped with whipped cream of course! According to the Starbucks menu online their frappuccino has 57 grams of sugar and 59 grams of carbs in one 16 ounce serving!"],
    ['how much coffee is in a mocha frappe from starbucks?', 'It also has 5g of protein and 75mg of caffeine. The Mocha Cookie Crumble Frappucino pours a blend of coffee, milk and ice atop whipped cream and chocolate cookie crumble. The whole thing is topped with a blend of rich mocha sauce and Frappuccino chips.'],
    ['how much coffee is in a mocha frappe from starbucks?', 'There are 460 calories in 1 serving of Starbucks Java Chip Frappuccino Blended Coffee with Whipped Cream (Grande).'],
    ['how much coffee is in a mocha frappe from starbucks?', 'Each 14 fl. oz bottle contains 250 calories, 4.5 grams of fat, 38 grams of sugar, and 150 milligrams of caffeine. So, while certainly not the healthiest option, they are convenient for anyone who loves iced Starbucks lattes. The drink is inspired by the Salted Caramel Mocha served seasonally at Starbucks stores.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'how much coffee is in a mocha frappe from starbucks?',
    [
        'The Mocha Frappuccino Light Blended Beverage has slightly more caffeine: Tall - 60 mg. Grande - 95 mg. Venti Iced - 120 mg.',
        "Typically Starbucks Vanilla Bean Frappuccino has no coffee in it at all. I believe it's made with sweetened condensed milk, vanilla bean powder and ice and topped with whipped cream of course! According to the Starbucks menu online their frappuccino has 57 grams of sugar and 59 grams of carbs in one 16 ounce serving!",
        'It also has 5g of protein and 75mg of caffeine. The Mocha Cookie Crumble Frappucino pours a blend of coffee, milk and ice atop whipped cream and chocolate cookie crumble. The whole thing is topped with a blend of rich mocha sauce and Frappuccino chips.',
        'There are 460 calories in 1 serving of Starbucks Java Chip Frappuccino Blended Coffee with Whipped Cream (Grande).',
        'Each 14 fl. oz bottle contains 250 calories, 4.5 grams of fat, 38 grams of sugar, and 150 milligrams of caffeine. So, while certainly not the healthiest option, they are convenient for anyone who loves iced Starbucks lattes. The drink is inspired by the Salted Caramel Mocha served seasonally at Starbucks stores.',
    ]
)
# [{'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"
      ],
      "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: 2,749,365 training samples
• Columns: <code>question</code>, <code>answer</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	question	answer	label
  type	string	string	int
  details	<ul><li>min: 19 characters</li><li>mean: 42.48 characters</li><li>max: 86 characters</li></ul>	<ul><li>min: 52 characters</li><li>mean: 249.98 characters</li><li>max: 382 characters</li></ul>	<ul><li>0: ~81.60%</li><li>1: ~18.40%</li></ul>

• Samples:

  question	answer	label
  <code>how much coffee is in a mocha frappe from starbucks?</code>	<code>The Mocha Frappuccino Light Blended Beverage has slightly more caffeine: Tall - 60 mg. Grande - 95 mg. Venti Iced - 120 mg.</code>	<code>1</code>
  <code>how much coffee is in a mocha frappe from starbucks?</code>	<code>Typically Starbucks Vanilla Bean Frappuccino has no coffee in it at all. I believe it's made with sweetened condensed milk, vanilla bean powder and ice and topped with whipped cream of course! According to the Starbucks menu online their frappuccino has 57 grams of sugar and 59 grams of carbs in one 16 ounce serving!</code>	<code>0</code>
  <code>how much coffee is in a mocha frappe from starbucks?</code>	<code>It also has 5g of protein and 75mg of caffeine. The Mocha Cookie Crumble Frappucino pours a blend of coffee, milk and ice atop whipped cream and chocolate cookie crumble. The whole thing is topped with a blend of rich mocha sauce and Frappuccino chips.</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

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• dataloader_num_workers: 12
• load_best_model_at_end: True

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 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: {}
• 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: 12
• 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: 12
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: True
• 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}
• tp_size: 0
• 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

</details>

Training Logs

Framework Versions

• Python: 3.11.0
• Sentence Transformers: 4.0.1
• Transformers: 4.50.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.2
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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.* -->