tomaarsen/reranker-distilroberta-base-quora-duplicates

CrossEncoder based on distilbert/distilroberta-base

This is a Cross Encoder model finetuned from distilbert/distilroberta-base on the quora-duplicates dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• —Model Type: Cross Encoder
• —Base model: distilbert/distilroberta-base <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
• —Maximum Sequence Length: 514 tokens
• —Training Dataset:
• —quora-duplicates
• —Language: en <!-- - License: Unknown -->

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("sentence_transformers_model_id")
# Get scores for pairs...
pairs = [
    ['What is the step by step guide to invest in share market in india?', 'What is the step by step guide to invest in share market?'],
    ['What is the story of Kohinoor (Koh-i-Noor) Diamond?', 'What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?'],
    ['How can I increase the speed of my internet connection while using a VPN?', 'How can Internet speed be increased by hacking through DNS?'],
    ['Why am I mentally very lonely? How can I solve it?', 'Find the remainder when [math]23^{24}[/math] is divided by 24,23?'],
    ['Which one dissolve in water quikly sugar, salt, methane and carbon di oxide?', 'Which fish would survive in salt water?'],
]
scores = model.predict(pairs)
print(scores.shape)
# [5]

# ... or rank different texts based on similarity to a single text
ranks = model.rank(
    'What is the step by step guide to invest in share market in india?',
    [
        'What is the step by step guide to invest in share market?',
        'What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?',
        'How can Internet speed be increased by hacking through DNS?',
        'Find the remainder when [math]23^{24}[/math] is divided by 24,23?',
        'Which fish would survive in salt water?',
    ]
)
# [{'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 Classification

• —Datasets: quora-duplicates-dev and quora-duplicates-test
• —Evaluated with <code>CEClassificationEvaluator</code>

<!--

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

quora-duplicates

• —Dataset: quora-duplicates at 451a485
• —Size: 404,290 training samples
• —Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• —Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | <ul><li>min: 1 characters</li><li>mean: 59.15 characters</li><li>max: 354 characters</li></ul> | <ul><li>min: 6 characters</li><li>mean: 60.74 characters</li><li>max: 399 characters</li></ul> | <ul><li>0: ~64.20%</li><li>1: ~35.80%</li></ul> |
• —Samples: | sentence1 | sentence2 | label | |:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------|:---------------| | <code>What are the features of the Indian caste system?</code> | <code>What triggers you the most when you play video games?</code> | <code>0</code> | | <code>What is the best place to learn Mandarin Chinese in Singapore?</code> | <code>What is the best place in Singapore for durian in December?</code> | <code>0</code> | | <code>What will be Hillary Clinton's India policy if she wins the election?</code> | <code>How would the bilateral relationship between India and the USA be under Hillary Clinton's presidency?</code> | <code>1</code> |
• —Loss: <code>BinaryCrossEntropyLoss</code>

Evaluation Dataset

quora-duplicates

• —Dataset: quora-duplicates at 451a485
• —Size: 404,290 evaluation samples
• —Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• —Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | <ul><li>min: 11 characters</li><li>mean: 57.9 characters</li><li>max: 244 characters</li></ul> | <ul><li>min: 12 characters</li><li>mean: 59.33 characters</li><li>max: 221 characters</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> |
• —Samples: | sentence1 | sentence2 | label | |:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------| | <code>What is the step by step guide to invest in share market in india?</code> | <code>What is the step by step guide to invest in share market?</code> | <code>0</code> | | <code>What is the story of Kohinoor (Koh-i-Noor) Diamond?</code> | <code>What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?</code> | <code>0</code> | | <code>How can I increase the speed of my internet connection while using a VPN?</code> | <code>How can Internet speed be increased by hacking through DNS?</code> | <code>0</code> |
• —Loss: <code>BinaryCrossEntropyLoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 64
• —per_device_eval_batch_size: 64
• —num_train_epochs: 1
• —warmup_ratio: 0.1
• —bf16: 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: 64
• —per_device_eval_batch_size: 64
• —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: 5e-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: 42
• —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: 0
• —dataloader_prefetch_factor: None
• —past_index: -1
• —disable_tqdm: False
• —remove_unused_columns: True
• —label_names: None
• —load_best_model_at_end: False
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• —Energy Consumed: 0.069 kWh
• —Carbon Emitted: 0.027 kg of CO2
• —Hours Used: 0.214 hours

Training Hardware

• —On Cloud: No
• —GPU Model: 1 x NVIDIA GeForce RTX 3090
• —CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• —RAM Size: 31.78 GB

Framework Versions

• —Python: 3.11.6
• —Sentence Transformers: 3.5.0.dev0
• —Transformers: 4.49.0.dev0
• —PyTorch: 2.5.0+cu121
• —Accelerate: 1.3.0
• —Datasets: 2.20.0
• —Tokenizers: 0.21.0

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. -->