--- base_model: BAAI/bge-m3 library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:6399 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: Instal·lació de tendals. sentences: - Quins són els exemples d'instal·lacions que es poden comunicar amb aquest tràmit? - Quin és el període en què es produeix la comunicació de tancament puntual d’una activitat? - Quin és el benefici del volant històric de convivència? - source_sentence: Ajuts econòmics destinats a reforçar les activitats econòmiques amb suspensió o limitació d’obertura al públic i per finançar les despeses de lloguer o hipoteca per empreses i/o establiments comercials sentences: - Quin és el tràmit per a realitzar una obra que canvia la distribució d’un local comercial? - Quan cal sol·licitar l'informe previ en matèria d'incendis? - Quin és el benefici dels ajuts econòmics per als treballadors? - source_sentence: L'Ajuntament concedirà als empleats municipals que tinguin al seu càrrec familiars amb discapacitat física, psíquica o sensorial, un ajut especial que es reportarà mensualment segons el grau de discapacitat. sentences: - Quin és el benefici que es reporta mensualment? - Quin és el resultat de la comunicació de canvi de titularitat a l'Ajuntament? - Quin és el requisit per renovar la inscripció en el Registre municipal de sol·licitants d'habitatge amb protecció oficial de Sitges? - source_sentence: El volant històric de convivència és el document que informa de la residencia en el municipi de Sitges, així com altres fets relatius a l'empadronament d'una persona, i detalla tots els domicilis, la data inicial i final en els que ha estat empadronada en cadascun d'ells, i les persones amb les què constava inscrites, segons les dades que consten al Padró Municipal d'Habitants fins a la data d'expedició. sentences: - Quin és el límit de potència instal·lada per a les instal·lacions de plaques solars en sòl urbà? - Quin és el contingut del Padró Municipal d'Habitants? - Quin és el resultat esperat de la gestió de les colònies felines? - source_sentence: Els comerços locals obtenen un benefici principal de la implementació del projecte d'implantació i ús de la targeta de fidelització del comerç local de Sitges, que és la possibilitat d'augmentar les vendes i la fidelització dels clients. sentences: - Quin és el benefici que els comerços locals obtenen de la implementació del projecte d'implantació i ús de la targeta de fidelització? - Quin és el pla d'ordenació urbanística municipal que regula l'ús d'habitatges d'ús turístic de Sitges? - Quin és el propòsit de la deixalleria municipal per a l’ambient? model-index: - name: SentenceTransformer based on BAAI/bge-m3 results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 1024 type: dim_1024 metrics: - type: cosine_accuracy@1 value: 0.13305203938115331 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.26244725738396624 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.35358649789029534 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5243319268635724 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.13305203938115331 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08748241912798875 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07071729957805907 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05243319268635724 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.13305203938115331 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.26244725738396624 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.35358649789029534 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5243319268635724 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2985567963545146 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.23013316812894896 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2512708543031996 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.13220815752461323 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.2630098452883263 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3541490857946554 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5285513361462728 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.13220815752461323 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08766994842944209 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07082981715893108 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05285513361462728 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.13220815752461323 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.2630098452883263 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3541490857946554 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5285513361462728 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.30111353887210784 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.2321642890630236 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2529696660722769 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.1341772151898734 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.26554149085794654 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3589310829817159 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5257383966244725 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.1341772151898734 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08851383028598217 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07178621659634317 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05257383966244726 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.1341772151898734 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.26554149085794654 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3589310829817159 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5257383966244725 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.3010502512929789 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.23285647310963767 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.25376075028724965 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.12658227848101267 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.26329113924050634 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3563994374120956 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5229254571026722 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.12658227848101267 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08776371308016878 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07127988748241912 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05229254571026722 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.12658227848101267 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.26329113924050634 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3563994374120956 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5229254571026722 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2971826978005507 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.22852298350188655 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.24963995627964844 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.12742616033755275 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.2683544303797468 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.35527426160337555 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5209563994374121 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.12742616033755275 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08945147679324894 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.0710548523206751 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05209563994374121 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.12742616033755275 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.2683544303797468 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.35527426160337555 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5209563994374121 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2973178953118737 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.22926059875426977 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2507076323664793 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.12236286919831224 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.2545710267229255 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3440225035161744 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5164556962025316 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.12236286919831224 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.0848570089076418 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06880450070323489 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05164556962025317 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.12236286919831224 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.2545710267229255 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3440225035161744 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5164556962025316 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.29092273297262244 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.22250820440693853 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2429016668571107 name: Cosine Map@100 --- # SentenceTransformer based on BAAI/bge-m3 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the json dataset. 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:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 1024 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - json ### 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## 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("adriansanz/ST-tramits-sitges-003-10ep") # Run inference sentences = [ "Els comerços locals obtenen un benefici principal de la implementació del projecte d'implantació i ús de la targeta de fidelització del comerç local de Sitges, que és la possibilitat d'augmentar les vendes i la fidelització dels clients.", "Quin és el benefici que els comerços locals obtenen de la implementació del projecte d'implantació i ús de la targeta de fidelització?", 'Quin és el propòsit de la deixalleria municipal per a l’ambient?', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `dim_1024` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1331 | | cosine_accuracy@3 | 0.2624 | | cosine_accuracy@5 | 0.3536 | | cosine_accuracy@10 | 0.5243 | | cosine_precision@1 | 0.1331 | | cosine_precision@3 | 0.0875 | | cosine_precision@5 | 0.0707 | | cosine_precision@10 | 0.0524 | | cosine_recall@1 | 0.1331 | | cosine_recall@3 | 0.2624 | | cosine_recall@5 | 0.3536 | | cosine_recall@10 | 0.5243 | | cosine_ndcg@10 | 0.2986 | | cosine_mrr@10 | 0.2301 | | **cosine_map@100** | **0.2513** | #### Information Retrieval * Dataset: `dim_768` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:----------| | cosine_accuracy@1 | 0.1322 | | cosine_accuracy@3 | 0.263 | | cosine_accuracy@5 | 0.3541 | | cosine_accuracy@10 | 0.5286 | | cosine_precision@1 | 0.1322 | | cosine_precision@3 | 0.0877 | | cosine_precision@5 | 0.0708 | | cosine_precision@10 | 0.0529 | | cosine_recall@1 | 0.1322 | | cosine_recall@3 | 0.263 | | cosine_recall@5 | 0.3541 | | cosine_recall@10 | 0.5286 | | cosine_ndcg@10 | 0.3011 | | cosine_mrr@10 | 0.2322 | | **cosine_map@100** | **0.253** | #### Information Retrieval * Dataset: `dim_512` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1342 | | cosine_accuracy@3 | 0.2655 | | cosine_accuracy@5 | 0.3589 | | cosine_accuracy@10 | 0.5257 | | cosine_precision@1 | 0.1342 | | cosine_precision@3 | 0.0885 | | cosine_precision@5 | 0.0718 | | cosine_precision@10 | 0.0526 | | cosine_recall@1 | 0.1342 | | cosine_recall@3 | 0.2655 | | cosine_recall@5 | 0.3589 | | cosine_recall@10 | 0.5257 | | cosine_ndcg@10 | 0.3011 | | cosine_mrr@10 | 0.2329 | | **cosine_map@100** | **0.2538** | #### Information Retrieval * Dataset: `dim_256` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1266 | | cosine_accuracy@3 | 0.2633 | | cosine_accuracy@5 | 0.3564 | | cosine_accuracy@10 | 0.5229 | | cosine_precision@1 | 0.1266 | | cosine_precision@3 | 0.0878 | | cosine_precision@5 | 0.0713 | | cosine_precision@10 | 0.0523 | | cosine_recall@1 | 0.1266 | | cosine_recall@3 | 0.2633 | | cosine_recall@5 | 0.3564 | | cosine_recall@10 | 0.5229 | | cosine_ndcg@10 | 0.2972 | | cosine_mrr@10 | 0.2285 | | **cosine_map@100** | **0.2496** | #### Information Retrieval * Dataset: `dim_128` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1274 | | cosine_accuracy@3 | 0.2684 | | cosine_accuracy@5 | 0.3553 | | cosine_accuracy@10 | 0.521 | | cosine_precision@1 | 0.1274 | | cosine_precision@3 | 0.0895 | | cosine_precision@5 | 0.0711 | | cosine_precision@10 | 0.0521 | | cosine_recall@1 | 0.1274 | | cosine_recall@3 | 0.2684 | | cosine_recall@5 | 0.3553 | | cosine_recall@10 | 0.521 | | cosine_ndcg@10 | 0.2973 | | cosine_mrr@10 | 0.2293 | | **cosine_map@100** | **0.2507** | #### Information Retrieval * Dataset: `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.1224 | | cosine_accuracy@3 | 0.2546 | | cosine_accuracy@5 | 0.344 | | cosine_accuracy@10 | 0.5165 | | cosine_precision@1 | 0.1224 | | cosine_precision@3 | 0.0849 | | cosine_precision@5 | 0.0688 | | cosine_precision@10 | 0.0516 | | cosine_recall@1 | 0.1224 | | cosine_recall@3 | 0.2546 | | cosine_recall@5 | 0.344 | | cosine_recall@10 | 0.5165 | | cosine_ndcg@10 | 0.2909 | | cosine_mrr@10 | 0.2225 | | **cosine_map@100** | **0.2429** | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 6,399 training samples * Columns: positive and anchor * Approximate statistics based on the first 1000 samples: | | positive | anchor | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | positive | anchor | |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | L'Ajuntament de Sitges atorga subvencions per a projectes i activitats d'interès públic o social que tinguin per finalitat les activitats esportives federades, escolars o populars desenvolupades per les entitats esportives i esportistes del municipi de Sitges. | Quin és el benefici de les subvencions per a les entitats esportives? | | L'Ajuntament de Sitges atorga subvencions per a projectes i activitats d'interès públic o social que tinguin per finalitat les activitats esportives federades, escolars o populars desenvolupades per les entitats esportives i esportistes del municipi de Sitges al llarg de l'exercici per la qual es sol·licita la subvenció, i reuneixin les condicions assenyalades a les bases. | Quin és el període d'execució dels projectes i activitats esportives? | | Certificat on s'indica el nombre d'habitatges que configuren el padró de l'Impost sobre Béns Immobles del municipi o bé d'una part d'aquest. | Quin és el contingut del certificat del nombre d'habitatges? | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 1024, 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `gradient_accumulation_steps`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 10 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.2 - `bf16`: True - `tf32`: True - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `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`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 16 - `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`: 10 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.2 - `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`: True - `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} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch_fused - `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 - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | dim_1024_cosine_map@100 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |:--------:|:-------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| | 0.4 | 10 | 3.5464 | - | - | - | - | - | - | | 0.8 | 20 | 2.3861 | - | - | - | - | - | - | | 1.0 | 25 | - | 0.2327 | 0.2144 | 0.2252 | 0.2286 | 0.1938 | 0.2329 | | 1.1975 | 30 | 1.8712 | - | - | - | - | - | - | | 1.5975 | 40 | 1.3322 | - | - | - | - | - | - | | 1.9975 | 50 | 0.9412 | 0.2410 | 0.2310 | 0.2383 | 0.2415 | 0.2236 | 0.2436 | | 2.395 | 60 | 0.806 | - | - | - | - | - | - | | 2.795 | 70 | 0.5024 | - | - | - | - | - | - | | 2.995 | 75 | - | 0.2451 | 0.2384 | 0.2455 | 0.2487 | 0.2323 | 0.2423 | | 3.1925 | 80 | 0.4259 | - | - | - | - | - | - | | 3.5925 | 90 | 0.3556 | - | - | - | - | - | - | | 3.9925 | 100 | 0.2555 | 0.2477 | 0.2443 | 0.2417 | 0.2485 | 0.2369 | 0.2470 | | 4.39 | 110 | 0.2611 | - | - | - | - | - | - | | 4.79 | 120 | 0.1939 | - | - | - | - | - | - | | 4.99 | 125 | - | 0.2490 | 0.2425 | 0.2479 | 0.2485 | 0.2386 | 0.2495 | | 5.1875 | 130 | 0.2021 | - | - | - | - | - | - | | 5.5875 | 140 | 0.1537 | - | - | - | - | - | - | | 5.9875 | 150 | 0.1277 | 0.2535 | 0.2491 | 0.2491 | 0.2534 | 0.2403 | 0.2541 | | 6.385 | 160 | 0.1213 | - | - | - | - | - | - | | 6.785 | 170 | 0.1035 | - | - | - | - | - | - | | 6.985 | 175 | - | 0.2513 | 0.2493 | 0.2435 | 0.2515 | 0.2380 | 0.2528 | | 7.1825 | 180 | 0.0965 | - | - | - | - | - | - | | 7.5825 | 190 | 0.0861 | - | - | - | - | - | - | | 7.9825 | 200 | 0.0794 | 0.2529 | 0.2536 | 0.2526 | 0.2545 | 0.2438 | 0.2570 | | 8.38 | 210 | 0.0734 | - | - | - | - | - | - | | 8.78 | 220 | 0.066 | - | - | - | - | - | - | | **8.98** | **225** | **-** | **0.2538** | **0.2523** | **0.2519** | **0.2542** | **0.2457** | **0.2572** | | 9.1775 | 230 | 0.0731 | - | - | - | - | - | - | | 9.5775 | 240 | 0.0726 | - | - | - | - | - | - | | 9.9775 | 250 | 0.0632 | 0.2513 | 0.2507 | 0.2496 | 0.2538 | 0.2429 | 0.2530 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.1.1 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.35.0.dev0 - Datasets: 3.0.1 - 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", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### 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} } ```