--- 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:9717 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss widget: - source_sentence: Per accedir a un habitatge amb protecció oficial al municipi de Sitges s'ha d'estar inscrit en el Registre municipal de sol·licitants. sentences: - Quin és el motiu perquè la renovació de la inscripció en el Registre municipal de sol·licitants d'habitatge amb protecció oficial de Sitges és necessària? - Quin és el sector que es veu afectat per la disminució d'ingressos? - Quin és el propòsit de la descripció de l'activitat? - source_sentence: Aquest tràmit permet presentar ofertes i/o pressupostos sol·licitats per l'Ajuntament de Sitges en procediments de contractes menors. sentences: - Quin és el requisit per a sol·licitar l'ajut econòmic a l'Ajuntament de Sitges? - Què passa amb la llicència de gual quan es vol reduir les característiques físiques? - Quin és el propòsit del tràmit de presentació d'ofertes? - source_sentence: Estudis universitaris fins al grau de llicenciatura sentences: - Quin és el propòsit de la subvenció per a les persones autònomes? - Quin és el requisit per als establiments oberts al públic destinats a espectacles públics i activitats recreatives musicals? - Quins estudis universitaris es poden fer amb aquesta ajuda? - source_sentence: Les entitats especialitzades i acreditades com a proveïdores de la Xarxa de Serveis Socials d'Atenció Pública interesades en la la gestió delegada dels serveis públics de l'Ajuntament de Sitges així determinats, poden presentar-se a les respectives convocatòries per a l'adjudicació. sentences: - On comencen i acaben les activitats de l'Estiu Jove? - Quin és el benefici per a l'Ajuntament de Sitges de la gestió delegada? - Quin és el paper de l’organització en la valoració d'una proposta? - source_sentence: Publicada la llista d'infants admesos i exclosos a les estades esportives, s'obre un termini perquè les persones admeses puguin demanar qualsevol canvi a la sol·licitud inicial. sentences: - Quin és el contingut del volant històric de convivència? - Quin és el període en què es pot demanar un canvi a la sol·licitud inicial? - Quin és el paper de les escoles de Sitges en les activitats de foment de l'esport escolar 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: 0.10126582278481013 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.18565400843881857 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.24472573839662448 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.34177215189873417 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.10126582278481013 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.061884669479606184 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.0489451476793249 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.03417721518987342 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.10126582278481013 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.18565400843881857 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.24472573839662448 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.34177215189873417 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.20497940546236365 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.1631588641082312 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.18190274772574827 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.0970464135021097 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.18143459915611815 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.2616033755274262 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.34177215189873417 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.0970464135021097 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.06047819971870604 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.052320675105485236 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.034177215189873406 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.0970464135021097 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.18143459915611815 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2616033755274262 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.34177215189873417 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.20447797235629017 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.16207219878105952 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.18114215201809386 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.08438818565400844 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.17721518987341772 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.23628691983122363 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.34177215189873417 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.08438818565400844 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.05907172995780591 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.04725738396624472 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.03417721518987342 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.08438818565400844 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.17721518987341772 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.23628691983122363 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.34177215189873417 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.19477348596574798 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.15014232134485297 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.16826302734813764 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.0759493670886076 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.16877637130801687 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.23628691983122363 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.34177215189873417 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.0759493670886076 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.05625879043600562 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.04725738396624473 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.034177215189873406 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.0759493670886076 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.16877637130801687 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.23628691983122363 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.34177215189873417 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.18887676996048183 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.14248208425423614 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.15960797563687307 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.08016877637130802 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.16455696202531644 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.2320675105485232 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.32489451476793246 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.08016877637130802 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.05485232067510549 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.046413502109704644 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.032489451476793246 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.08016877637130802 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.16455696202531644 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2320675105485232 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.32489451476793246 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.18920967116655296 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.14736454356707523 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.1622413863660417 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.046413502109704644 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.1518987341772152 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.21940928270042195 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.270042194092827 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.046413502109704644 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.050632911392405056 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.04388185654008439 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.0270042194092827 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.046413502109704644 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.1518987341772152 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.21940928270042195 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.270042194092827 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.15109586098353134 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.11371308016877635 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.12600329900444687 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/sitges-v2-5ep") # Run inference sentences = [ "Publicada la llista d'infants admesos i exclosos a les estades esportives, s'obre un termini perquè les persones admeses puguin demanar qualsevol canvi a la sol·licitud inicial.", 'Quin és el període en què es pot demanar un canvi a la sol·licitud inicial?', 'Quin és el contingut del volant històric de convivència?', ] 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 | 0.1013 | | cosine_accuracy@3 | 0.1857 | | cosine_accuracy@5 | 0.2447 | | cosine_accuracy@10 | 0.3418 | | cosine_precision@1 | 0.1013 | | cosine_precision@3 | 0.0619 | | cosine_precision@5 | 0.0489 | | cosine_precision@10 | 0.0342 | | cosine_recall@1 | 0.1013 | | cosine_recall@3 | 0.1857 | | cosine_recall@5 | 0.2447 | | cosine_recall@10 | 0.3418 | | cosine_ndcg@10 | 0.205 | | cosine_mrr@10 | 0.1632 | | **cosine_map@100** | **0.1819** | #### 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 | 0.097 | | cosine_accuracy@3 | 0.1814 | | cosine_accuracy@5 | 0.2616 | | cosine_accuracy@10 | 0.3418 | | cosine_precision@1 | 0.097 | | cosine_precision@3 | 0.0605 | | cosine_precision@5 | 0.0523 | | cosine_precision@10 | 0.0342 | | cosine_recall@1 | 0.097 | | cosine_recall@3 | 0.1814 | | cosine_recall@5 | 0.2616 | | cosine_recall@10 | 0.3418 | | cosine_ndcg@10 | 0.2045 | | cosine_mrr@10 | 0.1621 | | **cosine_map@100** | **0.1811** | #### 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 | 0.0844 | | cosine_accuracy@3 | 0.1772 | | cosine_accuracy@5 | 0.2363 | | cosine_accuracy@10 | 0.3418 | | cosine_precision@1 | 0.0844 | | cosine_precision@3 | 0.0591 | | cosine_precision@5 | 0.0473 | | cosine_precision@10 | 0.0342 | | cosine_recall@1 | 0.0844 | | cosine_recall@3 | 0.1772 | | cosine_recall@5 | 0.2363 | | cosine_recall@10 | 0.3418 | | cosine_ndcg@10 | 0.1948 | | cosine_mrr@10 | 0.1501 | | **cosine_map@100** | **0.1683** | #### 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 | 0.0759 | | cosine_accuracy@3 | 0.1688 | | cosine_accuracy@5 | 0.2363 | | cosine_accuracy@10 | 0.3418 | | cosine_precision@1 | 0.0759 | | cosine_precision@3 | 0.0563 | | cosine_precision@5 | 0.0473 | | cosine_precision@10 | 0.0342 | | cosine_recall@1 | 0.0759 | | cosine_recall@3 | 0.1688 | | cosine_recall@5 | 0.2363 | | cosine_recall@10 | 0.3418 | | cosine_ndcg@10 | 0.1889 | | cosine_mrr@10 | 0.1425 | | **cosine_map@100** | **0.1596** | #### 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 | 0.0802 | | cosine_accuracy@3 | 0.1646 | | cosine_accuracy@5 | 0.2321 | | cosine_accuracy@10 | 0.3249 | | cosine_precision@1 | 0.0802 | | cosine_precision@3 | 0.0549 | | cosine_precision@5 | 0.0464 | | cosine_precision@10 | 0.0325 | | cosine_recall@1 | 0.0802 | | cosine_recall@3 | 0.1646 | | cosine_recall@5 | 0.2321 | | cosine_recall@10 | 0.3249 | | cosine_ndcg@10 | 0.1892 | | cosine_mrr@10 | 0.1474 | | **cosine_map@100** | **0.1622** | #### 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 | 0.0464 | | cosine_accuracy@3 | 0.1519 | | cosine_accuracy@5 | 0.2194 | | cosine_accuracy@10 | 0.27 | | cosine_precision@1 | 0.0464 | | cosine_precision@3 | 0.0506 | | cosine_precision@5 | 0.0439 | | cosine_precision@10 | 0.027 | | cosine_recall@1 | 0.0464 | | cosine_recall@3 | 0.1519 | | cosine_recall@5 | 0.2194 | | cosine_recall@10 | 0.27 | | cosine_ndcg@10 | 0.1511 | | cosine_mrr@10 | 0.1137 | | **cosine_map@100** | **0.126** | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 9,717 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 al llarg de l'exercici per la qual es sol·licita la subvenció, i reuneixin les condicions assenyalades a les bases. | Quin és el requisit per a obtenir les subvencions per a projectes i activitats 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 requisit per a obtenir les subvencions per a projectes i activitats esportives? | | No es proporciona informació sobre el requisit principal per obtenir el certificat. | Quin és el requisit principal per obtenir el certificat? | * 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 | |:-------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| | 0.2632 | 10 | 3.2527 | - | - | - | - | - | - | | 0.5263 | 20 | 1.9679 | - | - | - | - | - | - | | 0.7895 | 30 | 1.8319 | - | - | - | - | - | - | | **1.0** | **38** | **-** | **0.1819** | **0.1622** | **0.1596** | **0.1683** | **0.126** | **0.1811** | | 1.0526 | 40 | 1.3358 | - | - | - | - | - | - | | 1.3158 | 50 | 1.1166 | - | - | - | - | - | - | | 1.5789 | 60 | 0.8715 | - | - | - | - | - | - | | 1.8421 | 70 | 0.8801 | - | - | - | - | - | - | | 2.0 | 76 | - | 0.1819 | 0.1622 | 0.1596 | 0.1683 | 0.1260 | 0.1811 | | 2.1053 | 80 | 0.6515 | - | - | - | - | - | - | | 2.3684 | 90 | 0.536 | - | - | - | - | - | - | | 2.6316 | 100 | 0.4682 | - | - | - | - | - | - | | 2.8947 | 110 | 0.4686 | - | - | - | - | - | - | | 3.0 | 114 | - | 0.1819 | 0.1622 | 0.1596 | 0.1683 | 0.1260 | 0.1811 | | 3.1579 | 120 | 0.3161 | - | - | - | - | - | - | | 3.4211 | 130 | 0.3554 | - | - | - | - | - | - | | 3.6842 | 140 | 0.2886 | - | - | - | - | - | - | | 3.9474 | 150 | 0.2616 | - | - | - | - | - | - | | 4.0 | 152 | - | 0.1819 | 0.1622 | 0.1596 | 0.1683 | 0.1260 | 0.1811 | | 4.2105 | 160 | 0.1902 | - | - | - | - | - | - | | 4.4737 | 170 | 0.1894 | - | - | - | - | - | - | | 4.7368 | 180 | 0.1858 | - | - | - | - | - | - | | 5.0 | 190 | 0.1939 | 0.1819 | 0.1622 | 0.1596 | 0.1683 | 0.1260 | 0.1811 | * 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} } ```