Push GCN + LTR + CE artifacts

206999a verified 6 days ago

13.6 kB

tags:
  - sentence-transformers
  - cross-encoder
  - reranker
  - generated_from_trainer
  - dataset_size:31340
  - loss:BinaryCrossEntropyLoss
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: 128 tokens
Number of Output Labels: 1 label
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

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 🤗 Hub
model = CrossEncoder("cross_encoder_model_id")
# Get scores for pairs of inputs
pairs = [
    ['حقيبة تشانك لوكس', "Globus Women's Textured Vegan Leather Sling Bag Tan | Globus Women Tan Vegan Leather Textured Sling Bag With Detachable Strap | globus | Crossbody Bags | Tan"],
    ['حريمية ماسكات كورية', 'Kappa 3-Pack Crew Socks Multicolour | Kappa Pack of 3 Crew Length Socks | Kappa | Socks | Multicolour'],
    ['شسي غير مبطنة', 'Fall In Love Unlined Bodysuit | فول إن لوف بودي سوت غير مبطن | DeFacto | Body Suits | Deep Magenta'],
    ['كندرة رموش مريحة للستات', 'Lift N Snatch Brow Tint Pen Black | قلم تحديد الحواجب ليفت أند سناتش رمادي أسود | NYX PROFESSIONAL MAKEUP | All Products | Black'],
    ['white blouse', '2Xtremz Schiffli Ruffle Cotton Top White | 2Xtremz Regular Fit Cotton Top with Schiffli and Ruffle Detail | 2Xtremz | Blouses | White'],
]
scores = model.predict(pairs)
print(scores)
# [0.9418 0.0044 0.978  0.2881 0.9463]

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'حقيبة تشانك لوكس',
    [
        "Globus Women's Textured Vegan Leather Sling Bag Tan | Globus Women Tan Vegan Leather Textured Sling Bag With Detachable Strap | globus | Crossbody Bags | Tan",
        'Kappa 3-Pack Crew Socks Multicolour | Kappa Pack of 3 Crew Length Socks | Kappa | Socks | Multicolour',
        'Fall In Love Unlined Bodysuit | فول إن لوف بودي سوت غير مبطن | DeFacto | Body Suits | Deep Magenta',
        'Lift N Snatch Brow Tint Pen Black | قلم تحديد الحواجب ليفت أند سناتش رمادي أسود | NYX PROFESSIONAL MAKEUP | All Products | Black',
        '2Xtremz Schiffli Ruffle Cotton Top White | 2Xtremz Regular Fit Cotton Top with Schiffli and Ruffle Detail | 2Xtremz | Blouses | White',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

Unnamed Dataset

Size: 31,340 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: 3 tokens mean: 7.44 tokens max: 19 tokens	min: 19 tokens mean: 37.84 tokens max: 57 tokens	min: 0.0 mean: 0.69 max: 1.0

Samples:

sentence_0	sentence_1	label
`حقيبة تشانك لوكس`	`Globus Women's Textured Vegan Leather Sling Bag Tan \| Globus Women Tan Vegan Leather Textured Sling Bag With Detachable Strap \| globus \| Crossbody Bags \| Tan`	`1.0`
`حريمية ماسكات كورية`	`Kappa 3-Pack Crew Socks Multicolour \| Kappa Pack of 3 Crew Length Socks \| Kappa \| Socks \| Multicolour`	`0.0`
`شسي غير مبطنة`	`Fall In Love Unlined Bodysuit \| فول إن لوف بودي سوت غير مبطن \| DeFacto \| Body Suits \| Deep Magenta`	`1.0`

Loss: BinaryCrossEntropyLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
fp16: True
disable_tqdm: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
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: 3
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: 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: True
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
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
dispatch_batches: None
split_batches: 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: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.5102	500	0.6826
1.0204	1000	0.4261
1.5306	1500	0.3741
2.0408	2000	0.3523
2.5510	2500	0.33

Training Time

Training: 5.3 minutes

Framework Versions

Python: 3.11.12
Sentence Transformers: 5.5.1
Transformers: 4.49.0
PyTorch: 2.7.0+cu128
Accelerate: 1.13.0
Datasets: 4.8.5
Tokenizers: 0.21.4

Additional Resources

Training and Finetuning Reranker Models with Sentence Transformers: the end-to-end guide for training or finetuning Cross Encoder (reranker) models.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video reranker models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: training multimodal Cross Encoders.

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",
}