|
|
--- |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- cross-encoder |
|
|
- reranker |
|
|
- generated_from_trainer |
|
|
- dataset_size:87398 |
|
|
- loss:CrossEntropyLoss |
|
|
base_model: deepvk/USER-bge-m3 |
|
|
pipeline_tag: text-classification |
|
|
library_name: sentence-transformers |
|
|
metrics: |
|
|
- f1_macro |
|
|
- f1_micro |
|
|
- f1_weighted |
|
|
model-index: |
|
|
- name: CrossEncoder based on deepvk/USER-bge-m3 |
|
|
results: |
|
|
- task: |
|
|
type: cross-encoder-softmax-accuracy |
|
|
name: Cross Encoder Softmax Accuracy |
|
|
dataset: |
|
|
name: softmax accuracy eval |
|
|
type: softmax_accuracy_eval |
|
|
metrics: |
|
|
- type: f1_macro |
|
|
value: 0.9715485242270209 |
|
|
name: F1 Macro |
|
|
- type: f1_micro |
|
|
value: 0.9743012183884509 |
|
|
name: F1 Micro |
|
|
- type: f1_weighted |
|
|
value: 0.974262256621189 |
|
|
name: F1 Weighted |
|
|
--- |
|
|
|
|
|
# CrossEncoder based on deepvk/USER-bge-m3 |
|
|
|
|
|
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [deepvk/USER-bge-m3](https://huggingface.co/deepvk/USER-bge-m3) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text pair classification. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
- **Model Type:** Cross Encoder |
|
|
- **Base model:** [deepvk/USER-bge-m3](https://huggingface.co/deepvk/USER-bge-m3) <!-- at revision 0cc6cfe48e260fb0474c753087a69369e88709ae --> |
|
|
- **Maximum Sequence Length:** 8192 tokens |
|
|
- **Number of Output Labels:** 2 labels |
|
|
<!-- - **Training Dataset:** Unknown --> |
|
|
<!-- - **Language:** Unknown --> |
|
|
<!-- - **License:** Unknown --> |
|
|
|
|
|
### 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 🤗 Hub |
|
|
model = CrossEncoder("Chimalpopoka/CrossEncoderRanker") |
|
|
# Get scores for pairs of texts |
|
|
pairs = [ |
|
|
['Панель аллергенов пыли № 1 IgE (домашняя пыль (Greer), клещ-дерматофаг перинный, клещ-дерматофаг мучной, таракан)', 'Смесь аллергенов пыли - hm1, Состав: домашняя пыль, Dermatophagoides pteronyssinus, Dermatophagoides farinae, таракан-прусак, IgE. Метод: ИФА'], |
|
|
['Жидкостная цитология РШМ', 'Жидкостная цитология. Исследование соскоба шейки матки и цервикального канала (окрашивание по Папаниколау)'], |
|
|
['Посев на возбудителей кишечной инфекции (сальмонеллы, шигеллы) с определением чувствительности к основному спектру антибиотиков', 'Посев кала на патогенную флору (дизентерийная и тифопаратифозная группы): С определением чувствительности к антибиотикам. Метод: культуральный'], |
|
|
['Молекулярно-генетическое исследование мутации в гене V617F (замена 617-ой аминокислоты с валина на фенилаланин) JAK2 (янус тирозин-киназа второго типа / Качественная оценка наличия соматической мутации V617F в 14 экзоне гена JAK2 (Qualitative assessment of presence of gene JAK2 617F somatic mutation)', 'Анализ мутации V617F гена JAK2 (замена валин на фенилаланин). Метод: ПЦР'], |
|
|
['Водородно-метановый дыхательный тест с лактулозой (СИБРТЕСТ, синдром избыточного бактериального роста в тонкой кишке, СИБР) (самостоятельное взятие проб)', 'Дыхательный водородный тест на СИБР'], |
|
|
] |
|
|
scores = model.predict(pairs) |
|
|
print(scores.shape) |
|
|
# (5, 2) |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### Direct Usage (Transformers) |
|
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Downstream Usage (Sentence Transformers) |
|
|
|
|
|
You can finetune this model on your own dataset. |
|
|
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Out-of-Scope Use |
|
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
|
--> |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
### Metrics |
|
|
|
|
|
#### Cross Encoder Softmax Accuracy |
|
|
|
|
|
* Dataset: `softmax_accuracy_eval` |
|
|
* Evaluated with [<code>CESoftmaxAccuracyEvaluator</code>](https://sbert.net/docs/package_reference/cross_encoder/evaluation.html#sentence_transformers.cross_encoder.evaluation.CESoftmaxAccuracyEvaluator) |
|
|
|
|
|
| Metric | Value | |
|
|
|:-------------|:-----------| |
|
|
| **f1_macro** | **0.9715** | |
|
|
| f1_micro | 0.9743 | |
|
|
| f1_weighted | 0.9743 | |
|
|
|
|
|
<!-- |
|
|
## Bias, Risks and Limitations |
|
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Recommendations |
|
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
|
--> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Dataset |
|
|
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 87,398 training samples |
|
|
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | sentence_0 | sentence_1 | label | |
|
|
|:--------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------| |
|
|
| type | string | string | int | |
|
|
| details | <ul><li>min: 5 characters</li><li>mean: 64.98 characters</li><li>max: 553 characters</li></ul> | <ul><li>min: 6 characters</li><li>mean: 63.31 characters</li><li>max: 477 characters</li></ul> | <ul><li>0: ~34.40%</li><li>1: ~65.60%</li></ul> | |
|
|
* Samples: |
|
|
| sentence_0 | sentence_1 | label | |
|
|
|:---------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------| |
|
|
| <code>Панель аллергенов пыли № 1 IgE (домашняя пыль (Greer), клещ-дерматофаг перинный, клещ-дерматофаг мучной, таракан)</code> | <code>Смесь аллергенов пыли - hm1, Состав: домашняя пыль, Dermatophagoides pteronyssinus, Dermatophagoides farinae, таракан-прусак, IgE. Метод: ИФА</code> | <code>1</code> | |
|
|
| <code>Жидкостная цитология РШМ</code> | <code>Жидкостная цитология. Исследование соскоба шейки матки и цервикального канала (окрашивание по Папаниколау)</code> | <code>1</code> | |
|
|
| <code>Посев на возбудителей кишечной инфекции (сальмонеллы, шигеллы) с определением чувствительности к основному спектру антибиотиков</code> | <code>Посев кала на патогенную флору (дизентерийная и тифопаратифозная группы): С определением чувствительности к антибиотикам. Метод: культуральный</code> | <code>1</code> | |
|
|
* Loss: [<code>CrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#crossentropyloss) |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: steps |
|
|
- `num_train_epochs`: 1 |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: steps |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 8 |
|
|
- `per_device_eval_batch_size`: 8 |
|
|
- `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`: 1 |
|
|
- `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 |
|
|
- `router_mapping`: {} |
|
|
- `learning_rate_mapping`: {} |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
| Epoch | Step | Training Loss | softmax_accuracy_eval_f1_macro | |
|
|
|:------:|:-----:|:-------------:|:------------------------------:| |
|
|
| 0.0458 | 500 | 0.5378 | - | |
|
|
| 0.0915 | 1000 | 0.2207 | - | |
|
|
| 0.1373 | 1500 | 0.2019 | - | |
|
|
| 0.1831 | 2000 | 0.1981 | 0.9654 | |
|
|
| 0.2288 | 2500 | 0.19 | - | |
|
|
| 0.2746 | 3000 | 0.1703 | - | |
|
|
| 0.3204 | 3500 | 0.217 | - | |
|
|
| 0.3661 | 4000 | 0.1673 | 0.9627 | |
|
|
| 0.4119 | 4500 | 0.1739 | - | |
|
|
| 0.4577 | 5000 | 0.143 | - | |
|
|
| 0.5034 | 5500 | 0.1522 | - | |
|
|
| 0.5492 | 6000 | 0.1545 | 0.9703 | |
|
|
| 0.5950 | 6500 | 0.1353 | - | |
|
|
| 0.6407 | 7000 | 0.1438 | - | |
|
|
| 0.6865 | 7500 | 0.1339 | - | |
|
|
| 0.7323 | 8000 | 0.1355 | 0.9715 | |
|
|
| 0.7780 | 8500 | 0.155 | - | |
|
|
| 0.8238 | 9000 | 0.1256 | - | |
|
|
| 0.8696 | 9500 | 0.1266 | - | |
|
|
| 0.9153 | 10000 | 0.1027 | 0.9715 | |
|
|
|
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.12.3 |
|
|
- Sentence Transformers: 5.1.0 |
|
|
- Transformers: 4.53.2 |
|
|
- PyTorch: 2.7.1+cu126 |
|
|
- Accelerate: 1.10.1 |
|
|
- 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", |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## Glossary |
|
|
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Authors |
|
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Contact |
|
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
|
--> |
