CrossEncoder based on nreimers/MiniLM-L6-H384-uncased

This is a Cross Encoder model finetuned from nreimers/MiniLM-L6-H384-uncased 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: nreimers/MiniLM-L6-H384-uncased
• Maximum Sequence Length: 512 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("ayushexel/reranker-MiniLM-L6-H384-uncased-gooaq-5-epoch-1995000")
# Get scores for pairs of texts
pairs = [
    ['when is the 2020 democratic presidential debate?', 'Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17–20, 2020 in Milwaukee, Wisconsin.'],
    ['when is the 2020 democratic presidential debate?', 'Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.'],
    ['when is the 2020 democratic presidential debate?', 'On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".'],
    ['when is the 2020 democratic presidential debate?', 'The electoral map for the 2020 election, based on populations from the 2010 Census. The 2020 United States presidential election is scheduled for Tuesday, November 3, 2020. It will be the 59th quadrennial presidential election.'],
    ['when is the 2020 democratic presidential debate?', 'There were a total of 29 major Democratic candidates. Of these, 23 candidates participated in at least one debate. Only Joe Biden and Bernie Sanders participated in all the debates; Pete Buttigieg, Amy Klobuchar, and Elizabeth Warren participated in all but one debate.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'when is the 2020 democratic presidential debate?',
    [
        'Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17–20, 2020 in Milwaukee, Wisconsin.',
        'Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.',
        'On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".',
        'The electoral map for the 2020 election, based on populations from the 2010 Census. The 2020 United States presidential election is scheduled for Tuesday, November 3, 2020. It will be the 59th quadrennial presidential election.',
        'There were a total of 29 major Democratic candidates. Of these, 23 candidates participated in at least one debate. Only Joe Biden and Bernie Sanders participated in all the debates; Pete Buttigieg, Amy Klobuchar, and Elizabeth Warren participated in all but one debate.',
    ]
)
# [{'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
  }
  

Cross Encoder Reranking

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

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

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
  }
  

Training Details

Training Dataset

Unnamed Dataset

• Size: 11,456,701 training samples
• Columns: question, answer, and label
• Approximate statistics based on the first 1000 samples:

  	question	answer	label
  type	string	string	int
  details	min: 18 characters mean: 43.15 characters max: 83 characters	min: 59 characters mean: 257.34 characters max: 388 characters	0: ~82.40% 1: ~17.60%

• Samples:

  question	answer	label
  when is the 2020 democratic presidential debate?	Major candidates The nomination will be made official at the 2020 Democratic National Convention, tentatively scheduled for August 17–20, 2020 in Milwaukee, Wisconsin.	1
  when is the 2020 democratic presidential debate?	Major candidates As of June 8, 2020, former Vice President Joe Biden became the presumptive presidential nominee by amassing enough delegates to secure the nomination.	0
  when is the 2020 democratic presidential debate?	On March 5, 2019, Bloomberg announced that he would not run for president in 2020; instead he encouraged the Democratic Party to "nominate a Democrat who will be in the strongest position to defeat Donald Trump".	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: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• dataloader_num_workers: 12
• 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: 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: 5
• 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

Training Logs

Click to expand

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",
}