devis-matcher / README.md
RavenAgent's picture
Initial upload: camembert-large fine-tune for French construction matching (v2, 14k pairs)
01590b8 verified
---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:14481
- loss:MultipleNegativesRankingLoss
base_model: Lajavaness/sentence-camembert-large
widget:
- source_sentence: Plomberie sanitaire
sentences:
- Semis manuel de pelouses à gazon, mauresques et ordinaires
- interne
- Installation sanitaire
- source_sentence: Charpente bois
sentences:
- Structure charpente
- Équipements sanitaires
- Installation pour le briquetage des garnitures de frein
- source_sentence: Machine à découper pour la découpe de la base des bandes et des
plaques aiguilletées
sentences:
- AVB-915
- Touret d'affûtage pour bandes et plaques à aiguilles
- section 200 x 400 mm
- source_sentence: plus de 32 cm
sentences:
- combustible gaz-mazout, capacité de production de vapeur 35-75 t/h, pression 3,9
MPa
- plus de 0,2 à 0,35 m3
- à la norme 01-02-104-01
- source_sentence: jusqu'à 25 m
sentences:
- à la norme 33-04-018-02
- 14,2 t
- jusqu'à 50 m
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
model-index:
- name: SentenceTransformer based on Lajavaness/sentence-camembert-large
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: eval
type: eval
metrics:
- type: pearson_cosine
value: .nan
name: Pearson Cosine
- type: spearman_cosine
value: .nan
name: Spearman Cosine
---
# SentenceTransformer based on Lajavaness/sentence-camembert-large
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Lajavaness/sentence-camembert-large](https://huggingface.co/Lajavaness/sentence-camembert-large). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [Lajavaness/sentence-camembert-large](https://huggingface.co/Lajavaness/sentence-camembert-large) <!-- at revision 4d78b025607a4fa3803e994520dade7c337441b8 -->
- **Maximum Sequence Length:** 514 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 514, 'do_lower_case': False, 'architecture': 'CamembertModel'})
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## 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 SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
"jusqu'à 25 m",
"jusqu'à 50 m",
'à la norme 33-04-018-02',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8389, 0.0886],
# [0.8389, 1.0000, 0.1294],
# [0.0886, 0.1294, 1.0000]])
```
<!--
### 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
#### Semantic Similarity
* Dataset: `eval`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:--------|
| pearson_cosine | nan |
| **spearman_cosine** | **nan** |
<!--
## 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: 14,481 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 3 tokens</li><li>mean: 13.16 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.46 tokens</li><li>max: 61 tokens</li></ul> |
* Samples:
| anchor | positive |
|:-----------------------------------------------------------------------|:------------------------------------------------------------------------|
| <code>Balances à plate-forme ; dispositif de recouvrement</code> | <code>Machine d'alumination</code> |
| <code>plus de 18 m², coefficient de résistance des roches 4 - 6</code> | <code>plus de 18 m², coefficient de résistance des roches 7 - 20</code> |
| <code>plus de 20 à 30 m dans les sols du groupe 1</code> | <code>plus de 20 à 30 m dans les sols du groupe 2</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Evaluation Dataset
#### Unnamed Dataset
* Size: 1,609 evaluation samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 3 tokens</li><li>mean: 12.72 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.04 tokens</li><li>max: 64 tokens</li></ul> |
* Samples:
| anchor | positive |
|:---------------------------------------|:---------------------------------------|
| <code>10 m3, groupe de sols 3 m</code> | <code>15 m3, groupe de sols 1 m</code> |
| <code>125-200 mm</code> | <code>250-400 mm</code> |
| <code>à la norme 01-01-032-05</code> | <code>à la norme 01-01-032-06</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 16
- `learning_rate`: 2e-05
- `num_train_epochs`: 5
- `warmup_steps`: 453
- `load_best_model_at_end`: True
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: epoch
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `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`: 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`: None
- `warmup_ratio`: 0.0
- `warmup_steps`: 453
- `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`: 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_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`: {}
</details>
### Training Logs
| Epoch | Step | Training Loss | Validation Loss | eval_spearman_cosine |
|:-------:|:--------:|:-------------:|:---------------:|:--------------------:|
| 0.5 | 453 | 0.5925 | - | - |
| 1.0 | 906 | 0.4408 | 0.2765 | nan |
| 1.5 | 1359 | 0.3219 | - | - |
| 2.0 | 1812 | 0.2956 | 0.2330 | nan |
| 2.5 | 2265 | 0.1923 | - | - |
| 3.0 | 2718 | 0.2017 | 0.2032 | nan |
| 3.5 | 3171 | 0.1307 | - | - |
| **4.0** | **3624** | **0.1151** | **0.1981** | **nan** |
| 4.5 | 4077 | 0.096 | - | - |
| 5.0 | 4530 | 0.0793 | 0.2025 | nan |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.9.6
- Sentence Transformers: 5.1.2
- Transformers: 4.57.6
- PyTorch: 2.8.0
- Accelerate: 1.10.1
- Datasets: 4.5.0
- Tokenizers: 0.22.2
## 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",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## 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.*
-->