--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:2560698 - loss:ModifiedMatryoshkaLoss base_model: google-bert/bert-base-multilingual-cased widget: - source_sentence: We got off the exit, we found a Shoney's restaurant. sentences: - Nos alejamos de la salida, comenzamos a buscar un -- encontramos un restaurante Shoney's. - Reduzcan sus emisiones de dióxido de carbono con todo el rango de opciones que tienen y luego compren o adquieran compensaciones para el resto que no han reducido completamente. - En el momento que nos invitaron a ir allí teníamos sede en San Francisco. Así que fuimos de un lado a otro durante el resto de 2009, pasando la mitad del tiempo en el condado de Bertie. - source_sentence: And in the audio world that's when the microphone gets too close to its sound source, and then it gets in this self-destructive loop that creates a very unpleasant sound. sentences: - Y, en el mundo del audio, es cuando el micrófono se acerca demasiado a su fuente de sonido, y entra en este bucle autodestructivo que crea un sonido muy desagradable. - Tiene que ayudarles a alcanzar un compromiso equitativo, y a asegurar que una amplia coalición de partidarios locales regionales e internacionales les ayuden a implementar el acuerdo. - Y es un renegado y visionario absoluto, y esa es la razón por la que ahora vivo y trabajo allí. - source_sentence: Figure out some of the other options that are much better. sentences: - Así que no sólo estamos reclutando a las multinacionales, les estamos dando las herramientas para entregar este bien público, el respeto por los Derechos Humanos, y lo estamos verificando. - Piensen en otras de las opciones que son mucho mejores. - Termina la propiedad comunal de las tierras de reserva. - source_sentence: He is 16 years old, loves hunting and fishing and being outside and doing anything with his hands, and so for him, Studio H means that he can stay interested in his education through that hands-on engagement. sentences: - Tiene 16 años, le encanta cazar, pescar y estar al aire libre y hacer tareas manuales. Para él Studio H representa el nexo educativo mediante esa motivación práctica. - Carbón capturado y secuestrado -- eso es lo que CCS significa -- es probable que se convierta en la aplicación determinante que nos posibilitará continuar utilizando combustibles fósiles en un modo que sea seguro. - El condado de Bertie no es la excepción. - source_sentence: There are thousands of these blue dots all over the county. sentences: - Me gusta crisis climática en vez de colapso climático, pero de nuevo, aquellos de ustedes que son buenos en diseño de marcas, necesito su ayuda en esto. - Si miran con cuidado, se ve que su cráneo ha sido sustituido por una cúpula transparente de plexiglás así que el funcionamiento de su cerebro se puede observar y controlar con luz. - Hay miles de estos puntos azules en todo el condado. pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - negative_mse model-index: - name: SentenceTransformer based on google-bert/bert-base-multilingual-cased results: - task: type: knowledge-distillation name: Knowledge Distillation dataset: name: MSE val en es type: MSE-val-en-es metrics: - type: negative_mse value: -31.070706248283386 name: Negative Mse - task: type: knowledge-distillation name: Knowledge Distillation dataset: name: MSE val en pt type: MSE-val-en-pt metrics: - type: negative_mse value: -31.284737586975098 name: Negative Mse - task: type: knowledge-distillation name: Knowledge Distillation dataset: name: MSE val en pt br type: MSE-val-en-pt-br metrics: - type: negative_mse value: -29.748335480690002 name: Negative Mse --- # SentenceTransformer based on google-bert/bert-base-multilingual-cased This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased). 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:** [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### 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': 128, 'do_lower_case': False}) with Transformer model: BertModel (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("luanafelbarros/bert-en-es-pt-matryoshka_v1") # Run inference sentences = [ 'There are thousands of these blue dots all over the county.', 'Hay miles de estos puntos azules en todo el condado.', 'Me gusta crisis climática en vez de colapso climático, pero de nuevo, aquellos de ustedes que son buenos en diseño de marcas, necesito su ayuda en esto.', ] 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 #### Knowledge Distillation * Datasets: `MSE-val-en-es`, `MSE-val-en-pt` and `MSE-val-en-pt-br` * Evaluated with [MSEEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator) | Metric | MSE-val-en-es | MSE-val-en-pt | MSE-val-en-pt-br | |:-----------------|:--------------|:--------------|:-----------------| | **negative_mse** | **-31.0707** | **-31.2847** | **-29.7483** | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 2,560,698 training samples * Columns: english, non_english, and label * Approximate statistics based on the first 1000 samples: | | english | non_english | label | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-------------------------------------| | type | string | string | list | | details | | | | * Samples: | english | non_english | label | |:-------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------| | And then there are certain conceptual things that can also benefit from hand calculating, but I think they're relatively small in number. | Y luego hay ciertas aspectos conceptuales que pueden beneficiarse del cálculo a mano pero creo que son relativamente pocos. | [-0.015244179405272007, 0.04601434990763664, -0.052873335778713226, 0.03535117208957672, -0.039562877267599106, ...] | | One thing I often ask about is ancient Greek and how this relates. | Algo que pregunto a menudo es sobre el griego antiguo y cómo se relaciona. | [0.0012022971641272306, -0.009590390138328075, -0.032977133989334106, 0.017047710716724396, -0.0028919472824782133, ...] | | See, the thing we're doing right now is we're forcing people to learn mathematics. | Vean, lo que estamos haciendo ahora es forzar a la gente a aprender matemáticas. | [-0.01942082867026329, 0.1043599545955658, 0.009455358609557152, -0.02814248949289322, -0.017036128789186478, ...] | * Loss: __main__.ModifiedMatryoshkaLoss with these parameters: ```json { "loss": "MSELoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 6,974 evaluation samples * Columns: english, non_english, and label * Approximate statistics based on the first 1000 samples: | | english | non_english | label | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-------------------------------------| | type | string | string | list | | details | | | | * Samples: | english | non_english | label | |:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------| | Thank you so much, Chris. | Muchas gracias Chris. | [-0.0616779625415802, -0.04450426995754242, -0.03250579163432121, -0.06641441583633423, 0.003981655463576317, ...] | | And it's truly a great honor to have the opportunity to come to this stage twice; I'm extremely grateful. | Y es en verdad un gran honor tener la oportunidad de venir a este escenario por segunda vez. Estoy extremadamente agradecido. | [0.011398598551750183, -0.02500401996076107, -0.009884790517389774, 0.009336900897324085, 0.003082842566072941, ...] | | I have been blown away by this conference, and I want to thank all of you for the many nice comments about what I had to say the other night. | He quedado conmovido por esta conferencia, y deseo agradecer a todos ustedes sus amables comentarios acerca de lo que tenía que decir la otra noche. | [-0.03842132166028023, 0.03635749593377113, -0.02491452544927597, -0.0032229204662144184, 0.0003549510147422552, ...] | * Loss: __main__.ModifiedMatryoshkaLoss with these parameters: ```json { "loss": "MSELoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 200 - `per_device_eval_batch_size`: 200 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `label_names`: ['label'] #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 200 - `per_device_eval_batch_size`: 200 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `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`: False - `fp16`: True - `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`: ['label'] - `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 - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `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 - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | MSE-val-en-es_negative_mse | MSE-val-en-pt_negative_mse | MSE-val-en-pt-br_negative_mse | |:------:|:-----:|:-------------:|:---------------:|:--------------------------:|:--------------------------:|:-----------------------------:| | 0.0781 | 1000 | 0.0252 | 0.0231 | -24.4152 | -24.3443 | -25.3002 | | 0.1562 | 2000 | 0.0222 | 0.0212 | -25.3038 | -25.3995 | -24.8563 | | 0.2343 | 3000 | 0.021 | 0.0204 | -27.0894 | -27.2195 | -26.2906 | | 0.3124 | 4000 | 0.0204 | 0.0198 | -28.7895 | -28.9815 | -28.0121 | | 0.3905 | 5000 | 0.02 | 0.0194 | -29.1917 | -29.3694 | -28.0828 | | 0.4686 | 6000 | 0.0196 | 0.0191 | -30.0902 | -30.2569 | -28.9723 | | 0.5467 | 7000 | 0.0194 | 0.0189 | -30.3385 | -30.5334 | -29.1280 | | 0.6248 | 8000 | 0.0192 | 0.0188 | -30.6629 | -30.8491 | -29.4291 | | 0.7029 | 9000 | 0.0191 | 0.0186 | -30.6934 | -30.8920 | -29.4820 | | 0.7810 | 10000 | 0.019 | 0.0185 | -31.0134 | -31.2205 | -29.6545 | | 0.8591 | 11000 | 0.0189 | 0.0185 | -31.0993 | -31.2950 | -29.8062 | | 0.9372 | 12000 | 0.0188 | 0.0184 | -31.0707 | -31.2847 | -29.7483 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.3.1 - Transformers: 4.46.3 - PyTorch: 2.5.1+cu121 - Accelerate: 1.1.1 - Datasets: 3.1.0 - Tokenizers: 0.20.3 ## 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", } ```