TakoData/chart-reranker

CrossEncoder based on Alibaba-NLP/gte-multilingual-reranker-base

This is a Cross Encoder model finetuned from Alibaba-NLP/gte-multilingual-reranker-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: Alibaba-NLP/gte-multilingual-reranker-base
• Maximum Sequence Length: 512 tokens
• Number of Output Labels: 1 label

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("cross_encoder_model_id")
# Get scores for pairs of texts
pairs = [
    ['What is the average rent price in Canada?', 'Title: "How many hours do Americans sleep at night (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov'],
    ['for the topic digital foortprint and identity use "\t " to give a description on if there was an provided teaching materials for this activity.', 'Title: "Different ways Americans define gender for someone who says they are transgender (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov'],
    ['Which U.S. cities or counties have the highest rates of aggravated assault involving a deadly weapon per 100,000 residents?', 'Title: "U.S. Bank Overview, CITY Overview"\nCollections: Companies\nDatasets: InstrumentClosePrice1Day\nChart Type: timeseries:eav_v3\nCanonical forms: "U.S. Bancorp"="closing_price", "Club De Futbol Intercity Sad"="closing_price"'],
    ['Black identity topics', 'Title: "Different ways Americans define gender for someone who says they are transgender (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov'],
    ['Which company in the Interactive Media and Services category has the highest market capitalization?', 'Title: "DigiPlus Interactive. Capital Expenditure (Quarterly)"\nCollections: Companies\nDatasets: StandardIncomeStatement\nChart Type: timeseries:eav_v3\nCanonical forms: "Capital Expenditure"="capital_expenditure"\nSources: S&P Global'],
]
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 average rent price in Canada?',
    [
        'Title: "How many hours do Americans sleep at night (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov',
        'Title: "Different ways Americans define gender for someone who says they are transgender (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov',
        'Title: "U.S. Bank Overview, CITY Overview"\nCollections: Companies\nDatasets: InstrumentClosePrice1Day\nChart Type: timeseries:eav_v3\nCanonical forms: "U.S. Bancorp"="closing_price", "Club De Futbol Intercity Sad"="closing_price"',
        'Title: "Different ways Americans define gender for someone who says they are transgender (United States)"\nCollections: YouGov Trackers\nDatasets: YouGovTrackerValueV2\nChart Type: survey:timeseries\nSources: YouGov',
        'Title: "DigiPlus Interactive. Capital Expenditure (Quarterly)"\nCollections: Companies\nDatasets: StandardIncomeStatement\nChart Type: timeseries:eav_v3\nCanonical forms: "Capital Expenditure"="capital_expenditure"\nSources: S&P Global',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Correlation

• Dataset: validation
• Evaluated with CrossEncoderCorrelationEvaluator

Metric	Value
pearson	0.8755
spearman	0.8709

Training Details

Training Dataset

Unnamed Dataset

• Size: 24,588 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	min: 3 characters mean: 88.65 characters max: 998 characters	min: 73 characters mean: 169.97 characters max: 352 characters	min: 0.0 mean: 0.41 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  What is the average rent price in Canada?	Title: "How many hours do Americans sleep at night (United States)" Collections: YouGov Trackers Datasets: YouGovTrackerValueV2 Chart Type: survey:timeseries Sources: YouGov	0.0
  for the topic digital foortprint and identity use " " to give a description on if there was an provided teaching materials for this activity.	Title: "Different ways Americans define gender for someone who says they are transgender (United States)" Collections: YouGov Trackers Datasets: YouGovTrackerValueV2 Chart Type: survey:timeseries Sources: YouGov	0.25
  Which U.S. cities or counties have the highest rates of aggravated assault involving a deadly weapon per 100,000 residents?	Title: "U.S. Bank Overview, CITY Overview" Collections: Companies Datasets: InstrumentClosePrice1Day Chart Type: timeseries:eav_v3 Canonical forms: "U.S. Bancorp"="closing_price", "Club De Futbol Intercity Sad"="closing_price"	0.0

• 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: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 5
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 5
• 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
• bf16: False
• fp16: True
• 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}
• 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: 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: 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
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	validation_spearman
0.1300	100	-	0.7581
0.2601	200	-	0.7928
0.3901	300	-	0.8105
0.5202	400	-	0.8252
0.6502	500	0.4726	0.8306
0.7802	600	-	0.8338
0.9103	700	-	0.8398
1.0	769	-	0.8406
1.0403	800	-	0.8412
1.1704	900	-	0.8479
1.3004	1000	0.4027	0.8525
1.4304	1100	-	0.8521
1.5605	1200	-	0.8549
1.6905	1300	-	0.8591
1.8205	1400	-	0.8619
1.9506	1500	0.3793	0.8614
2.0	1538	-	0.8627
2.0806	1600	-	0.8623
2.2107	1700	-	0.8641
2.3407	1800	-	0.8598
2.4707	1900	-	0.8655
2.6008	2000	0.3534	0.8641
2.7308	2100	-	0.8651
2.8609	2200	-	0.8656
2.9909	2300	-	0.8668
3.0	2307	-	0.8660
3.1209	2400	-	0.8678
3.2510	2500	0.3387	0.8654
3.3810	2600	-	0.8654
3.5111	2700	-	0.8667
3.6411	2800	-	0.8676
3.7711	2900	-	0.8674
3.9012	3000	0.3335	0.8704
4.0	3076	-	0.8703
4.0312	3100	-	0.8698
4.1612	3200	-	0.8709

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.1.2
• Transformers: 4.57.1
• PyTorch: 2.8.0+cu128
• Accelerate: 1.11.0
• Datasets: 4.2.0
• 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",
}