CrossEncoder based on cross-encoder/mmarco-mMiniLMv2-L12-H384-v1

This is a Cross Encoder model finetuned from cross-encoder/mmarco-mMiniLMv2-L12-H384-v1 on the arabic-ecom-data dataset 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: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
• Maximum Sequence Length: 128 tokens
• Number of Output Labels: 1 label
• Supported Modality: Text
• Training Dataset:
  • arabic-ecom-data

Model Sources

• Documentation: Sentence Transformers Documentation
• Documentation: Cross Encoder Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Cross Encoders on Hugging Face

Full Model Architecture

CrossEncoder(
  (0): Transformer({'transformer_task': 'sequence-classification', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'logits'}}, 'module_output_name': 'scores', 'architecture': 'XLMRobertaForSequenceClassification'})
)

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("leafxyz/arabic-ecom-cross-encoder-v3")
# Get scores for pairs of inputs
pairs = [
    ['مناديل مطبخ', 'صابون اواني جودي - 960 مل (الليمون الاخضر)'],
    ['جبنة هابي كاو', 'هابي كاو جبنة كريمى - 150 غ'],
    ['كريم تايغر للشعر', 'كريم ازالة شعر - Page Vine'],
    ['لانشون حلواني', 'لانشون حلواني دجاج - 250 غ'],
    ['صابون جودي 2.32', 'صابون اواني جودي برائحة الليمون الاخضر - 2.32 ل'],
]
scores = model.predict(pairs)
print(scores)
# [-5.0312  0.2981 -1.2588  0.6904  0.7002]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'مناديل مطبخ',
    [
        'صابون اواني جودي - 960 مل (الليمون الاخضر)',
        'هابي كاو جبنة كريمى - 150 غ',
        'كريم ازالة شعر - Page Vine',
        'لانشون حلواني دجاج - 250 غ',
        'صابون اواني جودي برائحة الليمون الاخضر - 2.32 ل',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

arabic-ecom-data

• Dataset: arabic-ecom-data
• Size: 246,013 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 3 tokensmean: 7.77 tokensmax: 20 tokens	min: 4 tokensmean: 13.06 tokensmax: 27 tokens	min: 0.0mean: 0.49max: 1.0

• Samples:

  sentence1	sentence2	label
  فلوتس أصبع	كيت كات شوكلاتة 4 اصابع 36.5 جم	0.0
  بخور عود ند شيخ العرب	بخور العود- اصل العود	0.0
  احمر شفاه Rhode	احمر شفاه - Water Lip Matte	0.0

• Loss: BinaryCrossEntropyLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Evaluation Dataset

arabic-ecom-data

• Dataset: arabic-ecom-data
• Size: 5,021 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 3 tokensmean: 7.86 tokensmax: 16 tokens	min: 4 tokensmean: 13.19 tokensmax: 33 tokens	min: 0.0mean: 0.48max: 1.0

• Samples:

  sentence1	sentence2	label
  مناديل مطبخ	صابون اواني جودي - 960 مل (الليمون الاخضر)	0.0
  جبنة هابي كاو	هابي كاو جبنة كريمى - 150 غ	1.0
  كريم تايغر للشعر	كريم ازالة شعر - Page Vine	0.0

• Loss: BinaryCrossEntropyLoss with these parameters:

  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "pos_weight": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 2
• warmup_steps: 0.1
• fp16: True

All Hyperparameters

• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 2
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: None
• warmup_steps: 0.1
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 21.4 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.4.1
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 5.0.0
• Tokenizers: 0.22.2

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",
}