ce-modernbert-trained-1epoch

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/ce-modernbert-trained-1epoch")
# Get scores for pairs of texts
pairs = [
    ['can you still get pregnant if you are infertile?', 'Many infertile couples will go on to conceive a child without treatment. After trying to get pregnant for two years, about 95 percent of couples successfully conceive.'],
    ['can you still get pregnant if you are infertile?', 'Secondary infertility is the inability to become pregnant or to carry a baby to term after previously giving birth to a baby. Secondary infertility shares many of the same causes of primary infertility. Secondary infertility might be caused by: Impaired sperm production, function or delivery in men.'],
    ['can you still get pregnant if you are infertile?', "Problems with cervical mucus can interfere with getting pregnant. Mild cases may increase the time it takes to get pregnant, but won't necessarily cause infertility."],
    ['can you still get pregnant if you are infertile?', 'No treatment can stop the process of diminished ovarian reserve, but women who are infertile due to low egg count or quality can sometimes use assisted reproductive technologies to achieve a pregnancy.'],
    ['can you still get pregnant if you are infertile?', "Human conception requires an egg and sperm. If you're not ovulating, you won't be able to get pregnant. Anovulation is a common cause of female infertility and it can be triggered by many conditions. Most women who are experiencing ovulation problems have irregular periods."],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'can you still get pregnant if you are infertile?',
    [
        'Many infertile couples will go on to conceive a child without treatment. After trying to get pregnant for two years, about 95 percent of couples successfully conceive.',
        'Secondary infertility is the inability to become pregnant or to carry a baby to term after previously giving birth to a baby. Secondary infertility shares many of the same causes of primary infertility. Secondary infertility might be caused by: Impaired sperm production, function or delivery in men.',
        "Problems with cervical mucus can interfere with getting pregnant. Mild cases may increase the time it takes to get pregnant, but won't necessarily cause infertility.",
        'No treatment can stop the process of diminished ovarian reserve, but women who are infertile due to low egg count or quality can sometimes use assisted reproductive technologies to achieve a pregnancy.',
        "Human conception requires an egg and sperm. If you're not ovulating, you won't be able to get pregnant. Anovulation is a common cause of female infertility and it can be triggered by many conditions. Most women who are experiencing ovulation problems have irregular periods.",
    ]
)
# [{'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: 18 characters</li><li>mean: 43.62 characters</li><li>max: 83 characters</li></ul>	<ul><li>min: 57 characters</li><li>mean: 250.11 characters</li><li>max: 396 characters</li></ul>	<ul><li>0: ~82.10%</li><li>1: ~17.90%</li></ul>

• Samples:

  question	answer	label
  <code>can you still get pregnant if you are infertile?</code>	<code>Many infertile couples will go on to conceive a child without treatment. After trying to get pregnant for two years, about 95 percent of couples successfully conceive.</code>	<code>1</code>
  <code>can you still get pregnant if you are infertile?</code>	<code>Secondary infertility is the inability to become pregnant or to carry a baby to term after previously giving birth to a baby. Secondary infertility shares many of the same causes of primary infertility. Secondary infertility might be caused by: Impaired sperm production, function or delivery in men.</code>	<code>0</code>
  <code>can you still get pregnant if you are infertile?</code>	<code>Problems with cervical mucus can interfere with getting pregnant. Mild cases may increase the time it takes to get pregnant, but won't necessarily cause infertility.</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.* -->