CrossEncoder based on FacebookAI/xlm-roberta-base

This is a Cross Encoder model finetuned from FacebookAI/xlm-roberta-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: FacebookAI/xlm-roberta-base
  • Maximum Sequence Length: 512 tokens
  • Number of Output Labels: 1 label
  • Supported Modality: Text

Model Sources

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 ๐Ÿค— Hub
model = CrossEncoder("cross_encoder_model_id")
# Get scores for pairs of inputs
pairs = [
    ['ะฉะพ ั‚ะฐะบะต feature engineering?', 'Feature engineering (ะบะพะฝัั‚ั€ัƒัŽะฒะฐะฝะฝั ะพะทะฝะฐะบ) ั†ะต ะฟั€ะพั†ะตั ะทะฐัั‚ะพััƒะฒะฐะฝะฝั ะทะฝะฐะฝัŒ ะฟั€ะตะดะผะตั‚ะฝะพั— ะณะฐะปัƒะทั– ะดะปั ัั‚ะฒะพั€ะตะฝะฝั ะพะทะฝะฐะบ, ัะบั– ะทะฐะฑะตะทะฟะตั‡ัƒัŽั‚ัŒ ั€ะพะฑะพั‚ัƒ ะฐะปะณะพั€ะธั‚ะผั–ะฒ ะผะฐัˆะธะฝะฝะพะณะพ ะฝะฐะฒั‡ะฐะฝะฝั.'],
    ['ะฉะพ ะฒะธะทะฝะฐั‡ะฐัŽั‚ัŒ ะฒะฐะณะธ ะฟั€ะตะดะธะบั‚ะพั€ั–ะฒ ัƒ ะปั–ะฝั–ะนะฝั–ะน ั€ะตะณั€ะตัั–ั—?', 'ะคะพั€ะผัƒะปะฐ ะปั–ะฝั–ะนะฝะพั— ั€ะตะณั€ะตัั–ั— (2.1):'],
    ['ะฏะบั– ัะฐะผะต ะฟะฐั€ะฐะผะตั‚ั€ะธ ะพั†ั–ะฝะบะธ ะผะพะดะตะปะตะน ะฟั€ะพะฟะพะฝัƒั”ั‚ัŒัั ะฝะฐะทะฒะฐั‚ะธ ะทะดะพะฑัƒะฒะฐั‡ะฐะผ?', 'ะขะพั‡ะฝั–ัั‚ัŒ ะฝะฐะนะบั€ะฐั‰ะพั— ะผะพะดะตะปั– ะฝะฐ ROC-ะบั€ะธะฒั–ะน (AUC-ROC) ัƒ ะทะฐะฒะดะฐะฝะฝั– ะปะฐะฑะพั€ะฐั‚ะพั€ะฝะพั— ั€ะพะฑะพั‚ะธ โ„–4 ะผะฐั” ะฑัƒั‚ะธ ะฝะต ะผะตะฝัˆะต 0.6.'],
    ['ะฉะพ ั‚ะฐะบะต ะฝะพ ะณั€ะฐะดะต ะฐะฑะพ torch.no_grad?', 'torch.no_grad() โ€” ะฝะต torch.no_gradient() ั‡ะธ torch.nograd(). ะ’ะธะบะพั€ะธัั‚ะพะฒัƒั”ั‚ัŒัั ัะบ ะบะพะฝั‚ะตะบัั‚ะฝะธะน ะผะตะฝะตะดะถะตั€.'],
    ['ะฏะบ ะทั€ะพะฑะธั‚ะธ ะผะฐะฟ ะฐะฑะพ map ั„ัƒะฝะบั†ั–ัŽ ะฝะฐ ะดะฐั‚ะฐัะตั‚ ัƒ ั…ะฐะณั–ะฝะณ ั„ะตะนั?', 'model.parameters() ะฟะตั€ะตะดะฐั”ั‚ัŒัั ะฒ ะพะฟั‚ะธะผั–ะทะฐั‚ะพั€: optimizer = torch.optim.Adam(model.parameters(), lr=1e-3).'],
]
scores = model.predict(pairs)
print(scores)
# [0.8542 0.0104 0.0106 0.9112 0.01  ]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'ะฉะพ ั‚ะฐะบะต feature engineering?',
    [
        'Feature engineering (ะบะพะฝัั‚ั€ัƒัŽะฒะฐะฝะฝั ะพะทะฝะฐะบ) ั†ะต ะฟั€ะพั†ะตั ะทะฐัั‚ะพััƒะฒะฐะฝะฝั ะทะฝะฐะฝัŒ ะฟั€ะตะดะผะตั‚ะฝะพั— ะณะฐะปัƒะทั– ะดะปั ัั‚ะฒะพั€ะตะฝะฝั ะพะทะฝะฐะบ, ัะบั– ะทะฐะฑะตะทะฟะตั‡ัƒัŽั‚ัŒ ั€ะพะฑะพั‚ัƒ ะฐะปะณะพั€ะธั‚ะผั–ะฒ ะผะฐัˆะธะฝะฝะพะณะพ ะฝะฐะฒั‡ะฐะฝะฝั.',
        'ะคะพั€ะผัƒะปะฐ ะปั–ะฝั–ะนะฝะพั— ั€ะตะณั€ะตัั–ั— (2.1):',
        'ะขะพั‡ะฝั–ัั‚ัŒ ะฝะฐะนะบั€ะฐั‰ะพั— ะผะพะดะตะปั– ะฝะฐ ROC-ะบั€ะธะฒั–ะน (AUC-ROC) ัƒ ะทะฐะฒะดะฐะฝะฝั– ะปะฐะฑะพั€ะฐั‚ะพั€ะฝะพั— ั€ะพะฑะพั‚ะธ โ„–4 ะผะฐั” ะฑัƒั‚ะธ ะฝะต ะผะตะฝัˆะต 0.6.',
        'torch.no_grad() โ€” ะฝะต torch.no_gradient() ั‡ะธ torch.nograd(). ะ’ะธะบะพั€ะธัั‚ะพะฒัƒั”ั‚ัŒัั ัะบ ะบะพะฝั‚ะตะบัั‚ะฝะธะน ะผะตะฝะตะดะถะตั€.',
        'model.parameters() ะฟะตั€ะตะดะฐั”ั‚ัŒัั ะฒ ะพะฟั‚ะธะผั–ะทะฐั‚ะพั€: optimizer = torch.optim.Adam(model.parameters(), lr=1e-3).',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Binary Classification

Metric Value
accuracy 0.8483
accuracy_threshold 0.3066
f1 0.8033
f1_threshold 0.175
precision 0.7076
recall 0.9289
average_precision 0.8038

Training Details

Training Dataset

Unnamed Dataset

  • Size: 5,691 training samples
  • Columns: sentence_0, sentence_1, and label
  • Approximate statistics based on the first 100 samples:
    sentence_0 sentence_1 label
    type string string float
    modality text text
    details
    • min: 5 tokens
    • mean: 16.56 tokens
    • max: 29 tokens
    • min: 7 tokens
    • mean: 37.74 tokens
    • max: 117 tokens
    • min: 0.0
    • mean: 0.36
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    ะฉะพ ั‚ะฐะบะต feature engineering? Feature engineering (ะบะพะฝัั‚ั€ัƒัŽะฒะฐะฝะฝั ะพะทะฝะฐะบ) ั†ะต ะฟั€ะพั†ะตั ะทะฐัั‚ะพััƒะฒะฐะฝะฝั ะทะฝะฐะฝัŒ ะฟั€ะตะดะผะตั‚ะฝะพั— ะณะฐะปัƒะทั– ะดะปั ัั‚ะฒะพั€ะตะฝะฝั ะพะทะฝะฐะบ, ัะบั– ะทะฐะฑะตะทะฟะตั‡ัƒัŽั‚ัŒ ั€ะพะฑะพั‚ัƒ ะฐะปะณะพั€ะธั‚ะผั–ะฒ ะผะฐัˆะธะฝะฝะพะณะพ ะฝะฐะฒั‡ะฐะฝะฝั. 0.0
    ะฉะพ ะฒะธะทะฝะฐั‡ะฐัŽั‚ัŒ ะฒะฐะณะธ ะฟั€ะตะดะธะบั‚ะพั€ั–ะฒ ัƒ ะปั–ะฝั–ะนะฝั–ะน ั€ะตะณั€ะตัั–ั—? ะคะพั€ะผัƒะปะฐ ะปั–ะฝั–ะนะฝะพั— ั€ะตะณั€ะตัั–ั— (2.1): 0.0
    ะฏะบั– ัะฐะผะต ะฟะฐั€ะฐะผะตั‚ั€ะธ ะพั†ั–ะฝะบะธ ะผะพะดะตะปะตะน ะฟั€ะพะฟะพะฝัƒั”ั‚ัŒัั ะฝะฐะทะฒะฐั‚ะธ ะทะดะพะฑัƒะฒะฐั‡ะฐะผ? ะขะพั‡ะฝั–ัั‚ัŒ ะฝะฐะนะบั€ะฐั‰ะพั— ะผะพะดะตะปั– ะฝะฐ ROC-ะบั€ะธะฒั–ะน (AUC-ROC) ัƒ ะทะฐะฒะดะฐะฝะฝั– ะปะฐะฑะพั€ะฐั‚ะพั€ะฝะพั— ั€ะพะฑะพั‚ะธ โ„–4 ะผะฐั” ะฑัƒั‚ะธ ะฝะต ะผะตะฝัˆะต 0.6. 0.0
  • Loss: BinaryCrossEntropyLoss with these parameters:
    {
        "activation_fn": "torch.nn.modules.linear.Identity",
        "pos_weight": null
    }
    

Training Hyperparameters

All Hyperparameters

Click to expand
  • per_device_train_batch_size: 8
  • num_train_epochs: 3
  • max_steps: -1
  • learning_rate: 5e-05
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_steps: 0
  • optim: adamw_torch_fused
  • optim_args: None
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • optim_target_modules: None
  • gradient_accumulation_steps: 1
  • average_tokens_across_devices: True
  • max_grad_norm: 1
  • label_smoothing_factor: 0.0
  • bf16: False
  • fp16: False
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • use_liger_kernel: False
  • liger_kernel_config: None
  • use_cache: False
  • neftune_noise_alpha: None
  • torch_empty_cache_steps: None
  • auto_find_batch_size: False
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • include_num_input_tokens_seen: no
  • log_level: passive
  • log_level_replica: warning
  • disable_tqdm: False
  • project: huggingface
  • trackio_space_id: None
  • trackio_bucket_id: None
  • trackio_static_space_id: None
  • per_device_eval_batch_size: 8
  • prediction_loss_only: True
  • eval_on_start: False
  • eval_do_concat_batches: True
  • eval_use_gather_object: False
  • eval_accumulation_steps: None
  • include_for_metrics: []
  • batch_eval_metrics: False
  • save_only_model: False
  • save_on_each_node: False
  • enable_jit_checkpoint: False
  • push_to_hub: False
  • hub_private_repo: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_always_push: False
  • hub_revision: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • restore_callback_states_from_checkpoint: False
  • full_determinism: False
  • seed: 42
  • data_seed: None
  • use_cpu: 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
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • dataloader_prefetch_factor: None
  • remove_unused_columns: True
  • label_names: None
  • train_sampling_strategy: random
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • ddp_static_graph: None
  • ddp_backend: None
  • ddp_timeout: 1800
  • fsdp: None
  • fsdp_config: None
  • deepspeed: None
  • debug: []
  • skip_memory_metrics: True
  • do_predict: False
  • resume_from_checkpoint: None
  • warmup_ratio: None
  • local_rank: -1
  • prompts: None
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss xlm-roberta-val_average_precision
0.2809 200 - 0.5829
0.5618 400 - 0.5270
0.7022 500 0.5999 -
0.8427 600 - 0.7588
1.0 712 - 0.6534
1.1236 800 - 0.7245
1.4045 1000 0.4367 0.6769
1.6854 1200 - 0.6549
1.9663 1400 - 0.7974
2.0 1424 - 0.7699
2.1067 1500 0.4249 -
2.2472 1600 - 0.7624
2.5281 1800 - 0.8038

Training Time

  • Training: 8.4 minutes

Framework Versions

  • Python: 3.12.13
  • Sentence Transformers: 5.5.1
  • Transformers: 5.10.1
  • PyTorch: 2.11.0+cu128
  • Accelerate: 1.13.0
  • Datasets: 4.0.0
  • Tokenizers: 0.22.2

Additional Resources

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",
}
Downloads last month
7
Safetensors
Model size
0.3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for IronPooh/xlm_roberta_hard_negatives

Finetuned
(4,322)
this model

Paper for IronPooh/xlm_roberta_hard_negatives

Evaluation results