Hugging Face's logo

foochun
/
bge-reranker-ft

Text Ranking
sentence-transformers
Safetensors
xlm-roberta
cross-encoder
Generated from Trainer
dataset_size:82744
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files
xet
 Community
bge-reranker-ft / README.md
foochun's picture
foochun
finetuned with additional names
c08f0f3 verified
preview code
|
raw
history blame contribute delete
13 kB
metadata 
tags:
  - sentence-transformers
  - cross-encoder
  - generated_from_trainer
  - dataset_size:82744
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-reranker-base
pipeline_tag: text-ranking
library_name: sentence-transformers

CrossEncoder based on BAAI/bge-reranker-base

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

Model Sources

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("foochun/bge-reranker-ft")
# Get scores for pairs of texts
pairs = [
    ['quinn toh heng yi', 'heng yi toh quinn'],
    ['mohd iskandi bin hassan', 'muhd iskandi hassan'],
    ['quinn ng ee siu', 'quinn ee siu ng'],
    ['malini doraisamy', 'malini doraisamy'],
    ['see shan fui', 'shanfui see'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'quinn toh heng yi',
    [
        'heng yi toh quinn',
        'muhd iskandi hassan',
        'quinn ee siu ng',
        'malini doraisamy',
        'shanfui see',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

Unnamed Dataset

  • Size: 82,744 training samples
  • Columns: query, pos, and neg
  • Approximate statistics based on the first 1000 samples:
    query pos neg
    type string string string
    details
    • min: 9 characters
    • mean: 19.16 characters
    • max: 42 characters
    • min: 9 characters
    • mean: 17.11 characters
    • max: 37 characters
    • min: 9 characters
    • mean: 17.7 characters
    • max: 38 characters
  • Samples:
    query pos neg
    brandon teh min jun jun teh min brandon min teh jun
    suling anak peroi suling anak peroi suling anak rahim
    chin sze tian szetian chin chin sze tian wong
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 10.0,
    "num_negatives": 4,
    "activation_fn": "torch.nn.modules.activation.Sigmoid"
}

Evaluation Dataset

Unnamed Dataset

  • Size: 11,820 evaluation samples
  • Columns: query, pos, and neg
  • Approximate statistics based on the first 1000 samples:
    query pos neg
    type string string string
    details
    • min: 10 characters
    • mean: 19.08 characters
    • max: 45 characters
    • min: 9 characters
    • mean: 17.02 characters
    • max: 40 characters
    • min: 9 characters
    • mean: 17.58 characters
    • max: 44 characters
  • Samples:
    query pos neg
    quinn toh heng yi heng yi toh quinn toh yi heng
    mohd iskandi bin hassan muhd iskandi hassan puteri balqis binti megat sulaiman
    quinn ng ee siu quinn ee siu ng quinn ee ng siu
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 10.0,
    "num_negatives": 4,
    "activation_fn": "torch.nn.modules.activation.Sigmoid"
}

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • learning_rate: 1e-05
  • warmup_ratio: 0.1
  • seed: 12
  • fp16: True
  • dataloader_num_workers: 4
  • load_best_model_at_end: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • 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: 1e-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: 12
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: 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: 4
  • 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}
  • 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
  • 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
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss
0.0008 1 0.4707
0.7734 1000 0.1114
1.5468 2000 0.0051
2.3202 3000 0.0046

Framework Versions

  • Python: 3.11.9
  • Sentence Transformers: 4.1.0
  • Transformers: 4.52.4
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.7.0
  • Datasets: 3.6.0
  • Tokenizers: 0.21.1

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",
}