README.md

---
tags:
- sentence-transformers
- cross-encoder
- reranker
- generated_from_trainer
- dataset_size:3190
- loss:ListNetLoss
base_model: sentence-transformers/all-mpnet-base-v2
pipeline_tag: text-ranking
library_name: sentence-transformers
---

# CrossEncoder based on sentence-transformers/all-mpnet-base-v2

This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) using the [sentence-transformers](https://www.SBERT.net) 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision e8c3b32edf5434bc2275fc9bab85f82640a19130 -->
- **Maximum Sequence Length:** 512 tokens
- **Number of Output Labels:** 1 label
<!-- - **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("Pranjal2002/all-mpnet-base-v2")
# Get scores for pairs of texts
pairs = [
    ['What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?', '10-K'],
    ['What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?', 'Earnings'],
    ['What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?', 'DEF14A'],
    ['What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?', '8-K'],
    ['What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?', '10-Q'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?',
    [
        '10-K',
        'Earnings',
        'DEF14A',
        '8-K',
        '10-Q',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
```

<!--
### 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.*
-->

<!--
## 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: 3,190 training samples
* Columns: <code>query</code>, <code>docs</code>, and <code>labels</code>
* Approximate statistics based on the first 1000 samples:
  |         | query                                                                                            | docs                               | labels                             |
  |:--------|:-------------------------------------------------------------------------------------------------|:-----------------------------------|:-----------------------------------|
  | type    | string                                                                                           | list                               | list                               |
  | details | <ul><li>min: 55 characters</li><li>mean: 103.12 characters</li><li>max: 180 characters</li></ul> | <ul><li>size: 5 elements</li></ul> | <ul><li>size: 5 elements</li></ul> |
* Samples:
  | query                                                                                                                                                                          | docs                                                       | labels                       |
  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------|:-----------------------------|
  | <code>What year over year growth rate was shown for paid memberships in the same table</code>                                                                                  | <code>['10-Q', '10-K', '8-K', 'Earnings', 'DEF14A']</code> | <code>[4, 3, 2, 1, 0]</code> |
  | <code>How did non‑GAAP EPS growth align with the incentive metrics set for management?</code>                                                                                  | <code>['DEF14A', '8-K', '10-K', '10-Q', 'Earnings']</code> | <code>[2, 1, 0, 0, 0]</code> |
  | <code>What questions were raised regarding Xcel Energy Inc.’s risk factors and mitigation plans related to the integration of renewable energy sources into their grid?</code> | <code>['10-K', 'Earnings', '8-K', '10-Q', 'DEF14A']</code> | <code>[4, 3, 2, 1, 0]</code> |
* Loss: [<code>ListNetLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#listnetloss) with these parameters:
  ```json
  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "mini_batch_size": null
  }
  ```

### Evaluation Dataset

#### Unnamed Dataset

* Size: 798 evaluation samples
* Columns: <code>query</code>, <code>docs</code>, and <code>labels</code>
* Approximate statistics based on the first 798 samples:
  |         | query                                                                                            | docs                               | labels                             |
  |:--------|:-------------------------------------------------------------------------------------------------|:-----------------------------------|:-----------------------------------|
  | type    | string                                                                                           | list                               | list                               |
  | details | <ul><li>min: 53 characters</li><li>mean: 102.91 characters</li><li>max: 179 characters</li></ul> | <ul><li>size: 5 elements</li></ul> | <ul><li>size: 5 elements</li></ul> |
* Samples:
  | query                                                                                                                                                          | docs                                                       | labels                       |
  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------|:-----------------------------|
  | <code>What consolidation trends among competitors are highlighted in disclosures affecting Regions Financial Corporation’s regional banking operations?</code> | <code>['10-K', 'Earnings', 'DEF14A', '8-K', '10-Q']</code> | <code>[4, 3, 2, 1, 0]</code> |
  | <code>How does Pentair manage equity award burn rate or share pool availability?</code>                                                                        | <code>['10-K', 'DEF14A', '10-Q', 'Earnings', '8-K']</code> | <code>[4, 3, 2, 1, 0]</code> |
  | <code>What key takeaways emerged from Valero Energy Corporation’s most recent earnings announcement?</code>                                                    | <code>['10-Q', '10-K', 'Earnings', '8-K', 'DEF14A']</code> | <code>[4, 3, 2, 1, 0]</code> |
* Loss: [<code>ListNetLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#listnetloss) with these parameters:
  ```json
  {
      "activation_fn": "torch.nn.modules.linear.Identity",
      "mini_batch_size": null
  }
  ```

### Training Hyperparameters
#### Non-Default Hyperparameters

- `eval_strategy`: steps
- `per_device_train_batch_size`: 4
- `per_device_eval_batch_size`: 4
- `gradient_accumulation_steps`: 2
- `learning_rate`: 2e-05
- `num_train_epochs`: 5
- `warmup_steps`: 100
- `bf16`: True
- `load_best_model_at_end`: True
- `optim`: adamw_torch

#### 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`: 4
- `per_device_eval_batch_size`: 4
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 2
- `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`: 5
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `warmup_steps`: 100
- `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`: 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
- `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 | Validation Loss |
|:---------:|:-------:|:-------------:|:---------------:|
| 0.1253    | 50      | 1.6075        | -               |
| 0.2506    | 100     | 1.5205        | -               |
| 0.3759    | 150     | 1.4374        | -               |
| 0.5013    | 200     | 1.3845        | 1.3822          |
| 0.6266    | 250     | 1.3679        | -               |
| 0.7519    | 300     | 1.3746        | -               |
| 0.8772    | 350     | 1.4091        | -               |
| 1.0025    | 400     | 1.3422        | 1.3904          |
| 1.1278    | 450     | 1.3553        | -               |
| 1.2531    | 500     | 1.3408        | -               |
| 1.3784    | 550     | 1.3326        | -               |
| 1.5038    | 600     | 1.3103        | 1.3707          |
| 1.6291    | 650     | 1.3377        | -               |
| 1.7544    | 700     | 1.3545        | -               |
| 1.8797    | 750     | 1.3357        | -               |
| **2.005** | **800** | **1.3403**    | **1.3394**      |
| 2.1303    | 850     | 1.3255        | -               |
| 2.2556    | 900     | 1.3354        | -               |
| 2.3810    | 950     | 1.3086        | -               |
| 2.5063    | 1000    | 1.3068        | 1.3520          |
| 2.6316    | 1050    | 1.3193        | -               |
| 2.7569    | 1100    | 1.3203        | -               |
| 2.8822    | 1150    | 1.317         | -               |
| 3.0075    | 1200    | 1.3212        | 1.3575          |
| 3.1328    | 1250    | 1.2905        | -               |
| 3.2581    | 1300    | 1.3045        | -               |
| 3.3835    | 1350    | 1.2826        | -               |
| 3.5088    | 1400    | 1.3314        | 1.3392          |
| 3.6341    | 1450    | 1.3094        | -               |
| 3.7594    | 1500    | 1.3134        | -               |
| 3.8847    | 1550    | 1.285         | -               |
| 4.0100    | 1600    | 1.295         | 1.3563          |
| 4.1353    | 1650    | 1.3003        | -               |
| 4.2607    | 1700    | 1.2871        | -               |
| 4.3860    | 1750    | 1.2837        | -               |
| 4.5113    | 1800    | 1.297         | 1.3536          |
| 4.6366    | 1850    | 1.2735        | -               |
| 4.7619    | 1900    | 1.2854        | -               |
| 4.8872    | 1950    | 1.295         | -               |

* The bold row denotes the saved checkpoint.

### Framework Versions
- Python: 3.12.11
- Sentence Transformers: 5.1.0
- Transformers: 4.56.1
- PyTorch: 2.8.0+cu126
- Accelerate: 1.10.1
- Datasets: 4.0.0
- Tokenizers: 0.22.0

## 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",
}
```

#### ListNetLoss
```bibtex
@inproceedings{cao2007learning,
    title={Learning to Rank: From Pairwise Approach to Listwise Approach},
    author={Cao, Zhe and Qin, Tao and Liu, Tie-Yan and Tsai, Ming-Feng and Li, Hang},
    booktitle={Proceedings of the 24th international conference on Machine learning},
    pages={129--136},
    year={2007}
}
```

<!--
## 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.*
-->