--- language: - de - en - es - fr - it - nl - pl - pt - ru - zh library_name: sentence-transformers tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:5749 - loss:CoSENTLoss base_model: ymelka/camembert-cosmetic-finetuned datasets: - PhilipMay/stsb_multi_mt metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max widget: - source_sentence: Nous nous déplaçons "... par rapport au cadre de repos cosmique en mouvement ... à environ 371 km/s vers la constellation du Lion". sentences: - La dame a fait frire la viande panée dans de l'huile chaude. - Il n'y a pas d'alambic qui ne soit pas relatif à un autre objet. - Le joueur de basket-ball est sur le point de marquer des points pour son équipe. - source_sentence: Le professeur Burkhauser a effectué des recherches approfondies sur les personnes qui sont pénalisées par l'augmentation du salaire minimum. sentences: - Un adolescent parle à une fille par le biais d'une webcam. - Une femme est en train de couper des oignons verts. - Les lois sur le salaire minimum nuisent le plus aux personnes les moins qualifiées et les moins productives. - source_sentence: Bien que le terme "reine" puisse faire référence à la fois à la reine régente (souveraine) ou à la reine consort, le roi a toujours été le souverain. sentences: - Des moutons paissent dans le champ devant une rangée d'arbres. - Il y a une très bonne raison de ne pas appeler le conjoint de la Reine "Roi" - parce qu'il n'est pas le Roi. - Un groupe de personnes âgées pose autour d'une table à manger. - source_sentence: Deux pygargues à tête blanche perchés sur une branche. sentences: - Un groupe de militaires joue dans un quintette de cuivres. - Deux aigles sont perchés sur une branche. - Un homme qui joue de la guitare sous la pluie. - source_sentence: Un homme joue de la guitare. sentences: - Il est possible qu'un système solaire comme le nôtre existe en dehors d'une galaxie. - Un homme joue de la flûte. - Un homme est en train de manger une banane. pipeline_tag: sentence-similarity model-index: - name: SentenceTransformer based on ymelka/camembert-cosmetic-finetuned results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: stsb fr dev type: stsb-fr-dev metrics: - type: pearson_cosine value: 0.6401461834329478 name: Pearson Cosine - type: spearman_cosine value: 0.6661576168424006 name: Spearman Cosine - type: pearson_manhattan value: 0.7077411059971963 name: Pearson Manhattan - type: spearman_manhattan value: 0.7104395816607704 name: Spearman Manhattan - type: pearson_euclidean value: 0.6183470655093759 name: Pearson Euclidean - type: spearman_euclidean value: 0.6339424060254548 name: Spearman Euclidean - type: pearson_dot value: 0.18614455072383299 name: Pearson Dot - type: spearman_dot value: 0.21677402345623561 name: Spearman Dot - type: pearson_max value: 0.7077411059971963 name: Pearson Max - type: spearman_max value: 0.7104395816607704 name: Spearman Max - type: pearson_cosine value: 0.834390325106948 name: Pearson Cosine - type: spearman_cosine value: 0.8564941342147334 name: Spearman Cosine - type: pearson_manhattan value: 0.8518548236293758 name: Pearson Manhattan - type: spearman_manhattan value: 0.854193303324745 name: Spearman Manhattan - type: pearson_euclidean value: 0.8541012365072966 name: Pearson Euclidean - type: spearman_euclidean value: 0.8555434573522197 name: Spearman Euclidean - type: pearson_dot value: 0.4989804086580052 name: Pearson Dot - type: spearman_dot value: 0.5094008186566353 name: Spearman Dot - type: pearson_max value: 0.8541012365072966 name: Pearson Max - type: spearman_max value: 0.8564941342147334 name: Spearman Max - task: type: semantic-similarity name: Semantic Similarity dataset: name: stsb fr test type: stsb-fr-test metrics: - type: pearson_cosine value: 0.7979696368103 name: Pearson Cosine - type: spearman_cosine value: 0.8219240068315988 name: Spearman Cosine - type: pearson_manhattan value: 0.8237827107867745 name: Pearson Manhattan - type: spearman_manhattan value: 0.8221440625680553 name: Spearman Manhattan - type: pearson_euclidean value: 0.8230384709547542 name: Pearson Euclidean - type: spearman_euclidean value: 0.8218369251066925 name: Spearman Euclidean - type: pearson_dot value: 0.4089365107737232 name: Pearson Dot - type: spearman_dot value: 0.4588995887587045 name: Spearman Dot - type: pearson_max value: 0.8237827107867745 name: Pearson Max - type: spearman_max value: 0.8221440625680553 name: Spearman Max --- # SentenceTransformer based on ymelka/camembert-cosmetic-finetuned This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [ymelka/camembert-cosmetic-finetuned](https://huggingface.co/ymelka/camembert-cosmetic-finetuned) on the [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) dataset. It maps sentences & paragraphs to a 768-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:** [ymelka/camembert-cosmetic-finetuned](https://huggingface.co/ymelka/camembert-cosmetic-finetuned) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) - **Languages:** de, en, es, fr, it, nl, pl, pt, ru, zh ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/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': 512, 'do_lower_case': False}) with Transformer model: CamembertModel (1): Pooling({'word_embedding_dimension': 768, '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("ymelka/camembert-cosmetic-similarity") # Run inference sentences = [ 'Un homme joue de la guitare.', 'Un homme est en train de manger une banane.', 'Un homme joue de la flûte.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `stsb-fr-dev` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.6401 | | **spearman_cosine** | **0.6662** | | pearson_manhattan | 0.7077 | | spearman_manhattan | 0.7104 | | pearson_euclidean | 0.6183 | | spearman_euclidean | 0.6339 | | pearson_dot | 0.1861 | | spearman_dot | 0.2168 | | pearson_max | 0.7077 | | spearman_max | 0.7104 | #### Semantic Similarity * Dataset: `stsb-fr-dev` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8344 | | **spearman_cosine** | **0.8565** | | pearson_manhattan | 0.8519 | | spearman_manhattan | 0.8542 | | pearson_euclidean | 0.8541 | | spearman_euclidean | 0.8555 | | pearson_dot | 0.499 | | spearman_dot | 0.5094 | | pearson_max | 0.8541 | | spearman_max | 0.8565 | #### Semantic Similarity * Dataset: `stsb-fr-test` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.798 | | **spearman_cosine** | **0.8219** | | pearson_manhattan | 0.8238 | | spearman_manhattan | 0.8221 | | pearson_euclidean | 0.823 | | spearman_euclidean | 0.8218 | | pearson_dot | 0.4089 | | spearman_dot | 0.4589 | | pearson_max | 0.8238 | | spearman_max | 0.8221 | ## Training Details ### Training Dataset #### PhilipMay/stsb_multi_mt * Dataset: [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c) * Size: 5,749 training samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence1 | sentence2 | score | |:-----------------------------------------------------------|:---------------------------------------------------------------------|:-------------------------------| | Un avion est en train de décoller. | Un avion est en train de décoller. | 5.0 | | Un homme joue d'une grande flûte. | Un homme joue de la flûte. | 3.799999952316284 | | Un homme étale du fromage râpé sur une pizza. | Un homme étale du fromage râpé sur une pizza non cuite. | 3.799999952316284 | * Loss: [CoSENTLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "pairwise_cos_sim" } ``` ### Evaluation Dataset #### PhilipMay/stsb_multi_mt * Dataset: [PhilipMay/stsb_multi_mt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c) * Size: 1,500 evaluation samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence1 | sentence2 | score | |:-------------------------------------------------------------------------|:----------------------------------------------------------------------------|:------------------| | Un homme avec un casque de sécurité est en train de danser. | Un homme portant un casque de sécurité est en train de danser. | 5.0 | | Un jeune enfant monte à cheval. | Un enfant monte à cheval. | 4.75 | | Un homme donne une souris à un serpent. | L'homme donne une souris au serpent. | 5.0 | * Loss: [CoSENTLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "pairwise_cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 2e-05 - `weight_decay`: 0.01 - `warmup_ratio`: 0.1 - `bf16`: 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`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.01 - `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`: 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`: 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`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `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 - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | loss | stsb-fr-dev_spearman_cosine | stsb-fr-test_spearman_cosine | |:------:|:----:|:-------------:|:------:|:---------------------------:|:----------------------------:| | 0 | 0 | - | - | 0.6661 | - | | 0.2778 | 100 | 4.9452 | 4.4417 | 0.7733 | - | | 0.5556 | 200 | 4.667 | 4.4273 | 0.7986 | - | | 0.8333 | 300 | 4.4904 | 4.3058 | 0.8338 | - | | 1.1111 | 400 | 4.1679 | 4.2723 | 0.8491 | - | | 1.3889 | 500 | 4.138 | 4.3575 | 0.8464 | - | | 1.6667 | 600 | 4.5737 | 4.3427 | 0.8479 | - | | 1.9444 | 700 | 4.3086 | 4.4455 | 0.8510 | - | | 2.2222 | 800 | 3.8711 | 4.4135 | 0.8590 | - | | 2.5 | 900 | 4.064 | 4.4775 | 0.8567 | - | | 2.7778 | 1000 | 4.2255 | 4.4733 | 0.8565 | - | | 3.0 | 1080 | - | - | - | 0.8219 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.41.2 - PyTorch: 2.3.0+cu121 - Accelerate: 0.31.0 - Datasets: 2.19.2 - Tokenizers: 0.19.1 ## 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", } ``` #### CoSENTLoss ```bibtex @online{kexuefm-8847, title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT}, author={Su Jianlin}, year={2022}, month={Jan}, url={https://kexue.fm/archives/8847}, } ```