--- tags: - sentence-transformers - cross-encoder - generated_from_trainer - dataset_size:1266 - loss:BinaryCrossEntropyLoss - dataset_size:13476 base_model: yoriis/arabert-tydi-ar pipeline_tag: text-ranking library_name: sentence-transformers --- # CrossEncoder based on yoriis/arabert-tydi-ar This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [yoriis/arabert-tydi-ar](https://huggingface.co/yoriis/arabert-tydi-ar) using the [sentence-transformers](https://www.SBERT.net) 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:** [yoriis/arabert-tydi-ar](https://huggingface.co/yoriis/arabert-tydi-ar) - **Maximum Sequence Length:** 512 tokens - **Number of Output Labels:** 1 label ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder) ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import CrossEncoder # Download from the ๐Ÿค— Hub model = CrossEncoder("yoriis/arabert-tydi-tafseer-quqa-ar") # Get scores for pairs of texts pairs = [ ['ู…ุง ุญุงู„ ุงู„ุฅู†ุณุงู† ุฅุฐุง ุฃุตุงุจู‡ ุงู„ุถุฑุŸ ', 'ูˆุฅุฐุง ู…ุณ ุงู„ุฅู†ุณุงู† ุงู„ุถุฑ ุฏุนุงู†ุง ู„ุฌู†ุจู‡ ุฃูˆ ู‚ุงุนุฏุง ุฃูˆ ู‚ุขุฆู…ุง ูู„ู…ุง ูƒุดูู†ุง ุนู†ู‡ ุถุฑู‡ ู…ุฑ ูƒุฃู† ู„ู… ูŠุฏุนู†ุง ุฅู„ู‰ ุถุฑ ู…ุณู‡ ูƒุฐู„ูƒ ุฒูŠู† ู„ู„ู…ุณุฑููŠู† ู…ุง ูƒุงู†ูˆุง ูŠุนู…ู„ูˆู†{12}ูŠูˆู†ุณ.'], ['ุจู…ุงุฐุง ูƒุงู† ู‡ู„ุงูƒ ู‚ูˆู… ู„ูˆุท\xa0ุนู„ูŠู‡ ุงู„ุณู„ุงู…\xa0 ุŸ', 'ูˆุงุฐูƒุฑูˆุง ุฅุฐ ุฌุนู„ูƒู… ุฎู„ูุงุก ู…ู† ุจุนุฏ ุนุงุฏ ูˆุจูˆุฃูƒู… ููŠ ุงู„ุฃุฑุถ ุชุชุฎุฐูˆู† ู…ู† ุณู‡ูˆู„ู‡ุง ู‚ุตูˆุฑุง ูˆุชู†ุญุชูˆู† ุงู„ุฌุจุงู„ ุจูŠูˆุชุง ูุงุฐูƒุฑูˆุง ุขู„ุงุก ุงู„ู„ู‡ ูˆู„ุง ุชุนุซูˆุง ููŠ ุงู„ุฃุฑุถ ู…ูุณุฏูŠู†{74} ุงู„ุฃุนุฑุงู'], ['ู…ุง ุฃุตุงุจ ุฃุญุฏ ู…ู† ู…ูƒุฑูˆู‡ ูุจุฅุฐู† ุงู„ู„ู‡ ุชุนุงู„ู‰ ูˆูŠุฌุจ ุงู„ุชุณู„ูŠู… ุจุฃู…ุฑ ุงู„ู„ู‡ ุชุนุงู„ู‰ . ุงุฐูƒุฑ ุงู„ุขูŠุฉ ุงู„ูƒุฑูŠู…ุฉ.', '\xa0ู…ุง ุฃุตุงุจ ู…ู† ู…ุตูŠุจุฉ ุฅู„ุง ุจุฅุฐู† ุงู„ู„ู‡ ูˆู…ู† ูŠุคู…ู† ุจุงู„ู„ู‡ ูŠู‡ุฏ ู‚ู„ุจู‡ ูˆุงู„ู„ู‡ ุจูƒู„ ุดูŠุก ุนู„ูŠู…{11}ุงู„ุชุบุงุจู†'], ['ู…ุงุฐุง ุชุนุชู‚ุฏ ุงู„ู†ุตุงุฑู‰ ููŠ ุนูŠุณู‰ ุงุจู† ู…ุฑูŠู… ุŸ', ' ู„ุง ูŠุณุชูˆูŠ ุงู„ู‚ุงุนุฏูˆู† ู…ู† ุงู„ู…ุคู…ู†ูŠู† ุบูŠุฑ ุฃูˆู„ูŠ ุงู„ุถุฑุฑ ูˆุงู„ู…ุฌุงู‡ุฏูˆู† ููŠ ุณุจูŠู„ ุงู„ู„ู‡ ุจุฃู…ูˆุงู„ู‡ู… ูˆุฃู†ูุณู‡ู… ูุถู„ ุงู„ู„ู‡ ุงู„ู…ุฌุงู‡ุฏูŠู† ุจุฃู…ูˆุงู„ู‡ู… ูˆุฃู†ูุณู‡ู… ุนู„ู‰ ุงู„ู‚ุงุนุฏูŠู† ุฏุฑุฌุฉ ูˆูƒู„ุง ูˆุนุฏ ุงู„ู„ู‡ ุงู„ุญุณู†ู‰ ูˆูุถู„ ุงู„ู„ู‡ ุงู„ู…ุฌุงู‡ุฏูŠู† ุนู„ู‰ ุงู„ู‚ุงุนุฏูŠู† ุฃุฌุฑุง ุนุธูŠู…ุง {95}ุงู„ู†ุณุงุก'], ['ู…ู† ู‡ู… ุงู„ุฐูŠู† ุฃู†ุนู… ุงู„ู„ู‡ ุนู„ูŠู‡ู… ุŸ', 'ุงู„ุฐูŠ ุฃุทุนู…ู‡ู… ู…ู† ุฌูˆุน ูˆุขู…ู†ู‡ู… ู…ู† ุฎูˆู{4} ู‚ุฑูŠุด'], ] scores = model.predict(pairs) print(scores.shape) # (5,) # Or rank different texts based on similarity to a single text ranks = model.rank( 'ู…ุง ุญุงู„ ุงู„ุฅู†ุณุงู† ุฅุฐุง ุฃุตุงุจู‡ ุงู„ุถุฑุŸ ', [ 'ูˆุฅุฐุง ู…ุณ ุงู„ุฅู†ุณุงู† ุงู„ุถุฑ ุฏุนุงู†ุง ู„ุฌู†ุจู‡ ุฃูˆ ู‚ุงุนุฏุง ุฃูˆ ู‚ุขุฆู…ุง ูู„ู…ุง ูƒุดูู†ุง ุนู†ู‡ ุถุฑู‡ ู…ุฑ ูƒุฃู† ู„ู… ูŠุฏุนู†ุง ุฅู„ู‰ ุถุฑ ู…ุณู‡ ูƒุฐู„ูƒ ุฒูŠู† ู„ู„ู…ุณุฑููŠู† ู…ุง ูƒุงู†ูˆุง ูŠุนู…ู„ูˆู†{12}ูŠูˆู†ุณ.', 'ูˆุงุฐูƒุฑูˆุง ุฅุฐ ุฌุนู„ูƒู… ุฎู„ูุงุก ู…ู† ุจุนุฏ ุนุงุฏ ูˆุจูˆุฃูƒู… ููŠ ุงู„ุฃุฑุถ ุชุชุฎุฐูˆู† ู…ู† ุณู‡ูˆู„ู‡ุง ู‚ุตูˆุฑุง ูˆุชู†ุญุชูˆู† ุงู„ุฌุจุงู„ ุจูŠูˆุชุง ูุงุฐูƒุฑูˆุง ุขู„ุงุก ุงู„ู„ู‡ ูˆู„ุง ุชุนุซูˆุง ููŠ ุงู„ุฃุฑุถ ู…ูุณุฏูŠู†{74} ุงู„ุฃุนุฑุงู', '\xa0ู…ุง ุฃุตุงุจ ู…ู† ู…ุตูŠุจุฉ ุฅู„ุง ุจุฅุฐู† ุงู„ู„ู‡ ูˆู…ู† ูŠุคู…ู† ุจุงู„ู„ู‡ ูŠู‡ุฏ ู‚ู„ุจู‡ ูˆุงู„ู„ู‡ ุจูƒู„ ุดูŠุก ุนู„ูŠู…{11}ุงู„ุชุบุงุจู†', ' ู„ุง ูŠุณุชูˆูŠ ุงู„ู‚ุงุนุฏูˆู† ู…ู† ุงู„ู…ุคู…ู†ูŠู† ุบูŠุฑ ุฃูˆู„ูŠ ุงู„ุถุฑุฑ ูˆุงู„ู…ุฌุงู‡ุฏูˆู† ููŠ ุณุจูŠู„ ุงู„ู„ู‡ ุจุฃู…ูˆุงู„ู‡ู… ูˆุฃู†ูุณู‡ู… ูุถู„ ุงู„ู„ู‡ ุงู„ู…ุฌุงู‡ุฏูŠู† ุจุฃู…ูˆุงู„ู‡ู… ูˆุฃู†ูุณู‡ู… ุนู„ู‰ ุงู„ู‚ุงุนุฏูŠู† ุฏุฑุฌุฉ ูˆูƒู„ุง ูˆุนุฏ ุงู„ู„ู‡ ุงู„ุญุณู†ู‰ ูˆูุถู„ ุงู„ู„ู‡ ุงู„ู…ุฌุงู‡ุฏูŠู† ุนู„ู‰ ุงู„ู‚ุงุนุฏูŠู† ุฃุฌุฑุง ุนุธูŠู…ุง {95}ุงู„ู†ุณุงุก', 'ุงู„ุฐูŠ ุฃุทุนู…ู‡ู… ู…ู† ุฌูˆุน ูˆุขู…ู†ู‡ู… ู…ู† ุฎูˆู{4} ู‚ุฑูŠุด', ] ) # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...] ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 13,476 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | label | |:--------|:-----------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | ู…ุง ุญุงู„ ุงู„ุฅู†ุณุงู† ุฅุฐุง ุฃุตุงุจู‡ ุงู„ุถุฑุŸ | ูˆุฅุฐุง ู…ุณ ุงู„ุฅู†ุณุงู† ุงู„ุถุฑ ุฏุนุงู†ุง ู„ุฌู†ุจู‡ ุฃูˆ ู‚ุงุนุฏุง ุฃูˆ ู‚ุขุฆู…ุง ูู„ู…ุง ูƒุดูู†ุง ุนู†ู‡ ุถุฑู‡ ู…ุฑ ูƒุฃู† ู„ู… ูŠุฏุนู†ุง ุฅู„ู‰ ุถุฑ ู…ุณู‡ ูƒุฐู„ูƒ ุฒูŠู† ู„ู„ู…ุณุฑููŠู† ู…ุง ูƒุงู†ูˆุง ูŠุนู…ู„ูˆู†{12}ูŠูˆู†ุณ. | 1.0 | | ุจู…ุงุฐุง ูƒุงู† ู‡ู„ุงูƒ ู‚ูˆู… ู„ูˆุทย ุนู„ูŠู‡ ุงู„ุณู„ุงู…ย  ุŸ | ูˆุงุฐูƒุฑูˆุง ุฅุฐ ุฌุนู„ูƒู… ุฎู„ูุงุก ู…ู† ุจุนุฏ ุนุงุฏ ูˆุจูˆุฃูƒู… ููŠ ุงู„ุฃุฑุถ ุชุชุฎุฐูˆู† ู…ู† ุณู‡ูˆู„ู‡ุง ู‚ุตูˆุฑุง ูˆุชู†ุญุชูˆู† ุงู„ุฌุจุงู„ ุจูŠูˆุชุง ูุงุฐูƒุฑูˆุง ุขู„ุงุก ุงู„ู„ู‡ ูˆู„ุง ุชุนุซูˆุง ููŠ ุงู„ุฃุฑุถ ู…ูุณุฏูŠู†{74} ุงู„ุฃุนุฑุงู | 0.0 | | ู…ุง ุฃุตุงุจ ุฃุญุฏ ู…ู† ู…ูƒุฑูˆู‡ ูุจุฅุฐู† ุงู„ู„ู‡ ุชุนุงู„ู‰ ูˆูŠุฌุจ ุงู„ุชุณู„ูŠู… ุจุฃู…ุฑ ุงู„ู„ู‡ ุชุนุงู„ู‰ . ุงุฐูƒุฑ ุงู„ุขูŠุฉ ุงู„ูƒุฑูŠู…ุฉ. | ย ู…ุง ุฃุตุงุจ ู…ู† ู…ุตูŠุจุฉ ุฅู„ุง ุจุฅุฐู† ุงู„ู„ู‡ ูˆู…ู† ูŠุคู…ู† ุจุงู„ู„ู‡ ูŠู‡ุฏ ู‚ู„ุจู‡ ูˆุงู„ู„ู‡ ุจูƒู„ ุดูŠุก ุนู„ูŠู…{11}ุงู„ุชุบุงุจู† | 1.0 | * Loss: [BinaryCrossEntropyLoss](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters: ```json { "activation_fn": "torch.nn.modules.linear.Identity", "pos_weight": null } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 4 #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `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 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `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`: False - `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`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `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 - `hub_revision`: None - `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 - `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 - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 0.5931 | 500 | 1.1727 | | 1.1862 | 1000 | 0.4899 | | 1.7794 | 1500 | 0.4133 | | 2.3725 | 2000 | 0.3503 | | 2.9656 | 2500 | 0.3202 | | 3.5587 | 3000 | 0.2675 | ### Framework Versions - Python: 3.11.13 - Sentence Transformers: 4.1.0 - Transformers: 4.53.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.9.0 - Datasets: 4.0.0 - Tokenizers: 0.21.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @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", } ```