README.md

metadata

language:
  - multilingual
license: cc-by-nc-4.0
tags:
  - sentence-transformers
  - cross-encoder
  - reranker
  - generated_from_trainer
  - dataset_size:13717
  - loss:BinaryCrossEntropyLoss
base_model: jinaai/jina-reranker-v2-base-multilingual
pipeline_tag: text-ranking
library_name: sentence-transformers
metrics:
  - map
  - mrr@10
  - ndcg@10
model-index:
  - name: cometadata/jina-reranker-v2-multilingual-affiliations
    results:
      - task:
          type: cross-encoder-reranking
          name: Cross Encoder Reranking
        dataset:
          name: affiliation val
          type: affiliation-val
        metrics:
          - type: map
            value: 0.9294
            name: Map
          - type: mrr@10
            value: 0.9294
            name: Mrr@10
          - type: ndcg@10
            value: 0.9564
            name: Ndcg@10

cometadata/jina-reranker-v2-multilingual-affiliations

This is a Cross Encoder model finetuned from jinaai/jina-reranker-v2-base-multilingual 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: jinaai/jina-reranker-v2-base-multilingual
• Maximum Sequence Length: 1024 tokens
• Number of Output Labels: 1 label
• Language: multilingual
• License: cc-by-nc-4.0

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("cometadata/jina-reranker-v2-multilingual-affiliations")
# Get scores for pairs of texts
pairs = [
    ["Centre sur le handicap et l'intégration, School of Economics and Political Science Université de Saint‐Gall", "College of Saint Benedict and Saint John's University, Collegeville, MN, United States"],
    ['Swiss Federal Institute of Technology (ETH) Zurich, Institute of Quantum Electronics, Laser Spectroscopy and Sensing Laboratory, Hoenggerberg, HPF D19, CH-8093\u2009Zurich, Switzerland', 'Laboratory of Crystallography, ETH Zurich, CH-8093 Zurich, Switzerland'],
    ['Swiss Federal Institute of Technology (ETH) Zurich, Institute of Quantum Electronics, Laser Spectroscopy and Sensing Laboratory, Hoenggerberg, HPF D19, CH-8093\u2009Zurich, Switzerland', "Laboratoire d'Electrochimie Physique et Analytique, École Polytechnique Fédérale de Lausanne Station 6, CH-1015 Lausanne, Switzerland"],
    ['Institute for Advanced Study, Technische Universität München 2 , Lichtenbergstr. 2a, D-85748 Garching, Germany', 'Department of Surgery, Technical University of Munich, School of Medicine, Munich, Germany'],
    ['Institute for Advanced Study, Technische Universität München 2 , Lichtenbergstr. 2a, D-85748 Garching, Germany', 'Lehrstuhl für BioMolekulare Optik, Ludwig-Maximilians-Universität München, Oettingenstrasse 67, 80538 München (Germany)'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    "Centre sur le handicap et l'intégration, School of Economics and Political Science Université de Saint‐Gall",
    [
        "College of Saint Benedict and Saint John's University, Collegeville, MN, United States",
        'Laboratory of Crystallography, ETH Zurich, CH-8093 Zurich, Switzerland',
        "Laboratoire d'Electrochimie Physique et Analytique, École Polytechnique Fédérale de Lausanne Station 6, CH-1015 Lausanne, Switzerland",
        'Department of Surgery, Technical University of Munich, School of Medicine, Munich, Germany',
        'Lehrstuhl für BioMolekulare Optik, Ludwig-Maximilians-Universität München, Oettingenstrasse 67, 80538 München (Germany)',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Reranking

• Dataset: affiliation-val
• Evaluated with CrossEncoderRerankingEvaluator with these parameters:

  {
      "at_k": 10,
      "always_rerank_positives": true
  }
  

Metric	Value
map	0.9294 (-0.0706)
mrr@10	0.9294 (-0.0706)
ndcg@10	0.9564 (-0.0436)

Training Details

Training Dataset

Unnamed Dataset

• Size: 13,717 training samples
• Columns: query, document, and label
• Approximate statistics based on the first 1000 samples:

  	query	document	label
  type	string	string	int
  details	min: 6 characters mean: 86.53 characters max: 273 characters	min: 8 characters mean: 88.5 characters max: 509 characters	0: ~50.00% 1: ~50.00%

• Samples:

  query	document	label
  Department of Otolaryngology-Head and Neck Surgery; National Defense Medical College; Saitama Japan	. Department of Otolaryngology-Head and Neck Surgery, National Defense Medical College, Japan.	1
  Department of Otolaryngology-Head and Neck Surgery; National Defense Medical College; Saitama Japan	EOG Resources, Inc	0
  School of Science and Engineering The Chinese University of Hong Kong,Shenzhen,China	School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China,	1

• Loss: BinaryCrossEntropyLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 2,421 evaluation samples
• Columns: query, document, and label
• Approximate statistics based on the first 1000 samples:

  	query	document	label
  type	string	string	int
  details	min: 10 characters mean: 100.92 characters max: 508 characters	min: 5 characters mean: 103.02 characters max: 504 characters	0: ~50.00% 1: ~50.00%

• Samples:

  query	document	label
  Centre sur le handicap et l'intégration, School of Economics and Political Science Université de Saint‐Gall	College of Saint Benedict and Saint John's University, Collegeville, MN, United States	0
  Swiss Federal Institute of Technology (ETH) Zurich, Institute of Quantum Electronics, Laser Spectroscopy and Sensing Laboratory, Hoenggerberg, HPF D19, CH-8093 Zurich, Switzerland	Laboratory of Crystallography, ETH Zurich, CH-8093 Zurich, Switzerland	1
  Swiss Federal Institute of Technology (ETH) Zurich, Institute of Quantum Electronics, Laser Spectroscopy and Sensing Laboratory, Hoenggerberg, HPF D19, CH-8093 Zurich, Switzerland	Laboratoire d'Electrochimie Physique et Analytique, École Polytechnique Fédérale de Lausanne Station 6, CH-1015 Lausanne, Switzerland	0

• Loss: BinaryCrossEntropyLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• warmup_ratio: 0.1
• bf16: True
• load_best_model_at_end: True
• push_to_hub: True
• hub_model_id: cometadata/jina-reranker-v2-multilingual-affiliations

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• 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: 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: 3
• 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
• 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: 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}
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• 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
• use_legacy_prediction_loop: False
• push_to_hub: True
• resume_from_checkpoint: None
• hub_model_id: cometadata/jina-reranker-v2-multilingual-affiliations
• 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: 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
• prompts: None
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	affiliation-val_ndcg@10
-1	-1	-	-	0.8997 (-0.1003)
0.0012	1	0.0941	-	-
0.1166	100	0.3775	-	-
0.2331	200	0.2667	-	-
0.3497	300	0.2155	-	-
0.4662	400	0.212	-	-
0.5828	500	0.2277	0.6306	0.9465 (-0.0535)
0.6993	600	0.2825	-	-
0.8159	700	0.2932	-	-
0.9324	800	0.3123	-	-
1.0490	900	0.2608	-	-
1.1655	1000	0.0833	0.5776	0.9543 (-0.0457)
1.2821	1100	0.0938	-	-
1.3986	1200	0.1492	-	-
1.5152	1300	0.1651	-	-
1.6317	1400	0.1842	-	-
1.7483	1500	0.2407	0.5891	0.9555 (-0.0445)
1.8648	1600	0.288	-	-
1.9814	1700	0.3352	-	-
2.0979	1800	0.1082	-	-
2.2145	1900	0.0758	-	-
2.3310	2000	0.1072	0.5725	0.9563 (-0.0437)
2.4476	2100	0.1437	-	-
2.5641	2200	0.153	-	-
2.6807	2300	0.2176	-	-
2.7972	2400	0.2513	-	-
2.9138	2500	0.2949	0.5721	0.9564 (-0.0436)
-1	-1	-	-	0.9564 (-0.0436)

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.0
• Transformers: 4.57.3
• PyTorch: 2.9.1+cu128
• Accelerate: 1.12.0
• Datasets: 4.4.2
• Tokenizers: 0.22.1

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",
}