--- 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:2844 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: La unió d’aquests dos documents conforma l’Informe d’Avaluació de l’Edifici (IAE). sentences: - Quin és el requisit per a rebre els ajuts econòmics per a les empreses? - Quin és el resultat de la unió de la Inspecció Tècnica de l’Edifici (ITE) i dels certificats energètics? - Quin és el termini per sol·licitar la renovació del carnet de persona cuidadora? - source_sentence: La Inspecció Tècnica dels Edificis (ITE) permet identificar les oportunitats de millora de l'eficiència energètica i implementar mesures de rehabilitació. sentences: - Quin és el benefici de l'activitat del Viver dels Avis de Sitges per a la qualitat de vida? - Com puc saber si puc ser cuidador? - Quin és el paper de la Inspecció Tècnica dels Edificis (ITE) en la millora de l'eficiència energètica? - source_sentence: A les zones blaves els parquímetres i serveis de pagament reconeixen les matricules dels vehicles acreditats. sentences: - Quin és el paper de la mediació en una denúncia? - Quin és el paper de les persones físiques? - Quin és el procediment per estacionar a les zones blaves amb l'acreditació de resident? - source_sentence: Els establiments oberts al públic destinats a espectacles cinematogràfics. Els establiments oberts al públic destinats a espectacles públics i activitats recreatives musicals amb un aforament autoritzat fins a 150 persones. sentences: - Quin és el resultat esperat després de la intervenció de l'Ajuntament en les denúncies sanitàries? - Quin és el requisit de superfície construïda per als restaurants musicals? - Quins establiments oberts al públic han de comunicar la seva obertura a l'Ajuntament? - source_sentence: El Decret 97/2002, de 5 de març, regula la concessió de la targeta d’aparcament per a persones amb disminució i altres mesures adreçades a facilitar el desplaçament de les persones amb mobilitat reduïda. sentences: - Quin és el benefici de la targeta d'aparcament per a les persones amb disminució? - Quin és el paper de la Junta de Govern Local? - Quin és l'organisme que emet el certificat de serveis prestats? 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: 0.11814345991561181 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.23277074542897327 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3129395218002813 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.4644163150492264 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.11814345991561181 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07759024847632442 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06258790436005626 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.046441631504922636 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.11814345991561181 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.23277074542897327 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3129395218002813 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.4644163150492264 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.26553370933458276 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.20527392672962277 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22599508422976106 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.11575246132208157 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.2289732770745429 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3112517580872011 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.46568213783403656 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.11575246132208157 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07632442569151429 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.062250351617440226 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.04656821378340366 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.11575246132208157 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.2289732770745429 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3112517580872011 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.46568213783403656 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.26414039995115557 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.20311873507021158 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22355973027797246 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.11912798874824192 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.23277074542897327 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.31758087201125174 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.46582278481012657 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.11912798874824192 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07759024847632444 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06351617440225035 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.04658227848101265 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.11912798874824192 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.23277074542897327 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.31758087201125174 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.46582278481012657 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.26671990925029193 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.20635646194717913 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22673055490318922 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.11533052039381153 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.22658227848101264 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.30857946554149085 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.45668073136427567 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.11533052039381153 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07552742616033756 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06171589310829817 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.04566807313642757 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.11533052039381153 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.22658227848101264 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.30857946554149085 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.45668073136427567 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.26044811042246035 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.20098218471636187 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22169039893772347 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.11181434599156118 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.22334739803094233 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.30253164556962026 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.45288326300984527 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.11181434599156118 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07444913267698076 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06050632911392405 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.045288326300984526 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.11181434599156118 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.22334739803094233 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.30253164556962026 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.45288326300984527 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2566428043422134 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.19724806331346384 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.21784479785600805 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.10689170182841069 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.21251758087201125 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.28846694796061884 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.42967651195499296 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.10689170182841069 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07083919362400375 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.05769338959212378 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0429676511954993 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.10689170182841069 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.21251758087201125 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.28846694796061884 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.42967651195499296 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2438421466584992 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.1875642957604982 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2080904354707231 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-006-5ep") # Run inference sentences = [ 'El Decret 97/2002, de 5 de març, regula la concessió de la targeta d’aparcament per a persones amb disminució i altres mesures adreçades a facilitar el desplaçament de les persones amb mobilitat reduïda.', "Quin és el benefici de la targeta d'aparcament per a les persones amb disminució?", 'Quin és el paper de la Junta de Govern Local?', ] 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 | 0.1181 | | cosine_accuracy@3 | 0.2328 | | cosine_accuracy@5 | 0.3129 | | cosine_accuracy@10 | 0.4644 | | cosine_precision@1 | 0.1181 | | cosine_precision@3 | 0.0776 | | cosine_precision@5 | 0.0626 | | cosine_precision@10 | 0.0464 | | cosine_recall@1 | 0.1181 | | cosine_recall@3 | 0.2328 | | cosine_recall@5 | 0.3129 | | cosine_recall@10 | 0.4644 | | cosine_ndcg@10 | 0.2655 | | cosine_mrr@10 | 0.2053 | | **cosine_map@100** | **0.226** | #### 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 | 0.1158 | | cosine_accuracy@3 | 0.229 | | cosine_accuracy@5 | 0.3113 | | cosine_accuracy@10 | 0.4657 | | cosine_precision@1 | 0.1158 | | cosine_precision@3 | 0.0763 | | cosine_precision@5 | 0.0623 | | cosine_precision@10 | 0.0466 | | cosine_recall@1 | 0.1158 | | cosine_recall@3 | 0.229 | | cosine_recall@5 | 0.3113 | | cosine_recall@10 | 0.4657 | | cosine_ndcg@10 | 0.2641 | | cosine_mrr@10 | 0.2031 | | **cosine_map@100** | **0.2236** | #### 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 | 0.1191 | | cosine_accuracy@3 | 0.2328 | | cosine_accuracy@5 | 0.3176 | | cosine_accuracy@10 | 0.4658 | | cosine_precision@1 | 0.1191 | | cosine_precision@3 | 0.0776 | | cosine_precision@5 | 0.0635 | | cosine_precision@10 | 0.0466 | | cosine_recall@1 | 0.1191 | | cosine_recall@3 | 0.2328 | | cosine_recall@5 | 0.3176 | | cosine_recall@10 | 0.4658 | | cosine_ndcg@10 | 0.2667 | | cosine_mrr@10 | 0.2064 | | **cosine_map@100** | **0.2267** | #### 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 | 0.1153 | | cosine_accuracy@3 | 0.2266 | | cosine_accuracy@5 | 0.3086 | | cosine_accuracy@10 | 0.4567 | | cosine_precision@1 | 0.1153 | | cosine_precision@3 | 0.0755 | | cosine_precision@5 | 0.0617 | | cosine_precision@10 | 0.0457 | | cosine_recall@1 | 0.1153 | | cosine_recall@3 | 0.2266 | | cosine_recall@5 | 0.3086 | | cosine_recall@10 | 0.4567 | | cosine_ndcg@10 | 0.2604 | | cosine_mrr@10 | 0.201 | | **cosine_map@100** | **0.2217** | #### 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 | 0.1118 | | cosine_accuracy@3 | 0.2233 | | cosine_accuracy@5 | 0.3025 | | cosine_accuracy@10 | 0.4529 | | cosine_precision@1 | 0.1118 | | cosine_precision@3 | 0.0744 | | cosine_precision@5 | 0.0605 | | cosine_precision@10 | 0.0453 | | cosine_recall@1 | 0.1118 | | cosine_recall@3 | 0.2233 | | cosine_recall@5 | 0.3025 | | cosine_recall@10 | 0.4529 | | cosine_ndcg@10 | 0.2566 | | cosine_mrr@10 | 0.1972 | | **cosine_map@100** | **0.2178** | #### 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 | 0.1069 | | cosine_accuracy@3 | 0.2125 | | cosine_accuracy@5 | 0.2885 | | cosine_accuracy@10 | 0.4297 | | cosine_precision@1 | 0.1069 | | cosine_precision@3 | 0.0708 | | cosine_precision@5 | 0.0577 | | cosine_precision@10 | 0.043 | | cosine_recall@1 | 0.1069 | | cosine_recall@3 | 0.2125 | | cosine_recall@5 | 0.2885 | | cosine_recall@10 | 0.4297 | | cosine_ndcg@10 | 0.2438 | | cosine_mrr@10 | 0.1876 | | **cosine_map@100** | **0.2081** | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 2,844 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? | | Per a poder ser beneficiari d'una subvenció per a un projecte o activitat cultural, les entitats o associacions culturals de Sitges han de tenir una seu social a la ciutat de Sitges i estar inscrites en el Registre d'Entitats de la Generalitat de Catalunya. | Quin és el requisit per a poder ser beneficiari d'una subvenció per a un projecte o activitat cultural? | | La cessió entre tercers, només es contempla en el cas de sepultures de construcció particular que hagin estat donades d'alta amb una anterioritat de 10 anys a la data de sol·licitud de la cessió. | Quin és el paper de la persona que, legalment hi tingui dret, en la cessió entre tercers? | * 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`: 5 - `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`: 5 - `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 | |:----------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| | 0.8989 | 10 | 3.2114 | - | - | - | - | - | - | | 0.9888 | 11 | - | 0.2144 | 0.2008 | 0.2070 | 0.2126 | 0.1842 | 0.2126 | | 1.7978 | 20 | 1.5622 | - | - | - | - | - | - | | 1.9775 | 22 | - | 0.2179 | 0.2101 | 0.2169 | 0.2180 | 0.2012 | 0.2193 | | 2.6966 | 30 | 0.7882 | - | - | - | - | - | - | | 2.9663 | 33 | - | 0.2239 | 0.2162 | 0.2220 | 0.2238 | 0.2070 | 0.2222 | | 3.5955 | 40 | 0.4956 | - | - | - | - | - | - | | 3.9551 | 44 | - | 0.2270 | 0.2177 | 0.2231 | 0.2278 | 0.2084 | 0.2255 | | 4.4944 | 50 | 0.392 | - | - | - | - | - | - | | **4.9438** | **55** | **-** | **0.226** | **0.2178** | **0.2217** | **0.2267** | **0.2081** | **0.2236** | * 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} } ```