baseten-admin/reranker-ModernBERT-base-gooaq-bce

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
• Maximum Sequence Length: 8192 tokens
• Number of Output Labels: 1 label
• 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("baseten-admin/reranker-ModernBERT-base-gooaq-bce")
# Get scores for pairs of texts
pairs = [
    ['how to put your phone on do not disturb on iphone?', 'Go to Settings > Do Not Disturb to turn on Do Not Disturb manually or set a schedule. to turn it on or off.'],
    ['how to put your phone on do not disturb on iphone?', "This icon means that your iPhone's Do Not Disturb feature is enabled."],
    ['how to put your phone on do not disturb on iphone?', 'About Do Not Disturb The Do Not Disturb option on the iPhone stops notifications, alerts and calls from making any noise, vibration or lighting up the phone screen when the screen is locked.'],
    ['how to put your phone on do not disturb on iphone?', 'Go to Settings > Do Not Disturb to turn on Do Not Disturb manually or set a schedule. to turn it on or off. If you set an alarm in the Clock app, the alarm goes off even when Do Not Disturb is on. Learn how to set and manage your alarms.'],
    ['how to put your phone on do not disturb on iphone?', "You can use the Do Not Disturb feature on your iPhone whenever you want to block any calls, texts, or other notifications from making your phone ring. The notifications and alerts will still be stored on your phone, and you can check them at any time, but your iPhone won't light up or ring."],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'how to put your phone on do not disturb on iphone?',
    [
        'Go to Settings > Do Not Disturb to turn on Do Not Disturb manually or set a schedule. to turn it on or off.',
        "This icon means that your iPhone's Do Not Disturb feature is enabled.",
        'About Do Not Disturb The Do Not Disturb option on the iPhone stops notifications, alerts and calls from making any noise, vibration or lighting up the phone screen when the screen is locked.',
        'Go to Settings > Do Not Disturb to turn on Do Not Disturb manually or set a schedule. to turn it on or off. If you set an alarm in the Clock app, the alarm goes off even when Do Not Disturb is on. Learn how to set and manage your alarms.',
        "You can use the Do Not Disturb feature on your iPhone whenever you want to block any calls, texts, or other notifications from making your phone ring. The notifications and alerts will still be stored on your phone, and you can check them at any time, but your iPhone won't light up or ring.",
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Reranking

• Dataset: gooaq-dev
• Evaluated with CrossEncoderRerankingEvaluator with these parameters:

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

Metric	Value
map	0.7246 (+0.1935)
mrr@10	0.7232 (+0.1992)
ndcg@10	0.7671 (+0.1759)

Cross Encoder Reranking

• Datasets: NanoMSMARCO_R100, NanoNFCorpus_R100 and NanoNQ_R100
• Evaluated with CrossEncoderRerankingEvaluator with these parameters:

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

Metric	NanoMSMARCO_R100	NanoNFCorpus_R100	NanoNQ_R100
map	0.4258 (-0.0638)	0.3246 (+0.0636)	0.4195 (-0.0001)
mrr@10	0.4133 (-0.0642)	0.5233 (+0.0235)	0.4245 (-0.0022)
ndcg@10	0.4863 (-0.0541)	0.3615 (+0.0364)	0.5073 (+0.0067)

Cross Encoder Nano BEIR

• Dataset: NanoBEIR_R100_mean
• Evaluated with CrossEncoderNanoBEIREvaluator with these parameters:

  {
      "dataset_names": [
          "msmarco",
          "nfcorpus",
          "nq"
      ],
      "rerank_k": 100,
      "at_k": 10,
      "always_rerank_positives": true
  }
  

Metric	Value
map	0.3899 (-0.0001)
mrr@10	0.4537 (-0.0143)
ndcg@10	0.4517 (-0.0036)

Training Details

Training Dataset

Unnamed Dataset

• Size: 578,402 training samples
• Columns: question, answer, and label
• Approximate statistics based on the first 1000 samples:

  	question	answer	label
  type	string	string	int
  details	min: 20 characters mean: 42.74 characters max: 83 characters	min: 51 characters mean: 250.28 characters max: 385 characters	0: ~82.30% 1: ~17.70%

• Samples:

  question	answer	label
  how to put your phone on do not disturb on iphone?	Go to Settings > Do Not Disturb to turn on Do Not Disturb manually or set a schedule. to turn it on or off.	1
  how to put your phone on do not disturb on iphone?	This icon means that your iPhone's Do Not Disturb feature is enabled.	0
  how to put your phone on do not disturb on iphone?	About Do Not Disturb The Do Not Disturb option on the iPhone stops notifications, alerts and calls from making any noise, vibration or lighting up the phone screen when the screen is locked.	0

• Loss: BinaryCrossEntropyLoss 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: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• dataloader_num_workers: 4
• load_best_model_at_end: 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: 16
• per_device_eval_batch_size: 16
• 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: 4
• 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

Training Logs

Epoch	Step	Training Loss	gooaq-dev_ndcg@10	NanoMSMARCO_R100_ndcg@10	NanoNFCorpus_R100_ndcg@10	NanoNQ_R100_ndcg@10	NanoBEIR_R100_mean_ndcg@10
-1	-1	-	0.1394 (-0.4518)	0.0204 (-0.5200)	0.2531 (-0.0719)	0.0693 (-0.4313)	0.1143 (-0.3411)
0.0002	1	1.2794	-	-	-	-	-
0.2213	1000	0.8021	-	-	-	-	-
0.4426	2000	0.5164	-	-	-	-	-
0.6639	3000	0.4769	-	-	-	-	-
0.8852	4000	0.4613	0.7671 (+0.1759)	0.4863 (-0.0541)	0.3615 (+0.0364)	0.5073 (+0.0067)	0.4517 (-0.0036)
-1	-1	-	0.7671 (+0.1759)	0.4863 (-0.0541)	0.3615 (+0.0364)	0.5073 (+0.0067)	0.4517 (-0.0036)

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 4.0.2
• Transformers: 4.50.0
• PyTorch: 2.6.0+cu124
• Accelerate: 1.5.2
• Datasets: 3.4.1
• 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",
}