--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:102127 - loss:SpladeLoss - loss:SparseMultipleNegativesRankingLoss - loss:FlopsLoss base_model: seregadgl/splade_gemma_google_base_checkpoint_100_clear widget: - source_sentence: 'query: 6460338 acdelco' sentences: - 'document: очиститель тормозов rsqprofessional арт 072589767pl volkswagen id buzz янтарный' - 'document: гтц 6460338 для chevrolet traverse' - 'document: гтц 6960358 для chevrolet traverse' - source_sentence: 'query: audioquest cinnamon usb 0 7500 см ' sentences: - 'document: кабель usb аудиоквест cinnamon 0 7500 см 8712516' - 'document: задняя камера рамке номерного знака интерпауэр ip616 54785862' - 'document: аудиокабель soundwave 200 см' - source_sentence: 'query: акустическое пианино weber w 121 pw ' sentences: - 'document: акустическое пианино steinway model s' - 'document: инструмент для игры на пианино вебер w 121 pw' - 'document: велосипед сильвербек strela sport 700c 54 см blue 60097000435025' - source_sentence: 'query: шкаф шрм24' sentences: - 'document: wardrobe shrm 24 4348563' - 'document: духовой шкаф бертаццони f6011provtn' - 'document: шкаф мдф30' - source_sentence: 'query: 1452634 santool jawa 300 cl' sentences: - 'document: смартфон эппл iphone xs max 512gb' - 'document: 1453934 santool съемник для сальников jawa 300 cl' - 'document: 1452634 santool съемник для сальников jawa 300 cl' datasets: - seregadgl/car_and_product_triplet_103k pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - 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 model-index: - name: SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear results: - task: type: information-retrieval name: Information Retrieval dataset: name: val set fine type: val_set_fine metrics: - type: cosine_accuracy@1 value: 0.742 name: Cosine Accuracy@1 - type: cosine_precision@1 value: 0.742 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.27633333333333326 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1728 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08910000000000001 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.742 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.829 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.864 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.891 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8160719769563038 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7919432539682544 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.7955622385483846 name: Cosine Map@100 --- # SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) on the [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'}) (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}) (2): SparseLayer( (linear): Linear(in_features=768, out_features=262144, bias=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("seregadgl/splade_gemma_google_base_checkpoint_100_ver2") # Run inference sentences = [ 'query: 1452634 santool jawa 300 cl', 'document: 1452634 santool съемник для сальников jawa 300 cl', 'document: 1453934 santool съемник для сальников jawa 300 cl', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.1443, 0.1452], # [0.1443, 1.0000, 0.7490], # [0.1452, 0.7490, 1.0000]]) ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `val_set_fine` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.742 | | cosine_precision@1 | 0.742 | | cosine_precision@3 | 0.2763 | | cosine_precision@5 | 0.1728 | | cosine_precision@10 | 0.0891 | | cosine_recall@1 | 0.742 | | cosine_recall@3 | 0.829 | | cosine_recall@5 | 0.864 | | cosine_recall@10 | 0.891 | | **cosine_ndcg@10** | **0.8161** | | cosine_mrr@10 | 0.7919 | | cosine_map@100 | 0.7956 | ## Training Details ### Training Dataset #### car_and_product_triplet_103k * Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2) * Size: 102,127 training samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:--------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------| | query: погружной блендер tefal optichef hb64f810 | document: погружной блендер тефаль optichef hb64f810 | document: погружной миксер tefal mixchef hb64f850 | | query: 375675836 niteo | document: тосол 375675836 для ford f350 полуночный синий | document: тосол 375625836 для ford f350 полуночный синий фиалковый | | query: накидка с подогревом dodge viper pink | document: накидка с подогревом acdelco арт 787327sx dodge viper розовый | document: 787327sx накидка с подогревом indian challenger лаймовый | * Loss: [SpladeLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters: ```json { "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)", "document_regularizer_weight": 1e-05, "query_regularizer_weight": 1e-05 } ``` ### Evaluation Dataset #### car_and_product_triplet_103k * Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2) * Size: 1,000 evaluation samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | query: зеркала для 'слепых' зон volkswagen arteon | document: зеркала для 'слепых' зон 86635985zz для volkswagen arteon перламутровочёрный | document: 86635985zz зеркала для 'слепых' зон иж юпитер2 голубой | | query: elf bar lux 1500 лимонад голубой малины 1500 | document: одноразовая электронная сигарета эльф бар 1 5000 мл lemonade blue raspberry 340440526 | document: elf bar vibe 1000 мохито зелёного яблока 1000 | | query: удалитель наклеек chevrolet corvette onyx | document: удалитель наклеек 20810588pl для chevrolet corvette оникс | document: удалитель наклеек 20810588pl для maserati levante янтарный | * Loss: [SpladeLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters: ```json { "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)", "document_regularizer_weight": 1e-05, "query_regularizer_weight": 1e-05 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `gradient_accumulation_steps`: 16 - `learning_rate`: 0.0001 - `num_train_epochs`: 1 - `warmup_steps`: 10 - `fp16`: True - `load_best_model_at_end`: True - `router_mapping`: {'query': 'anchor', 'document': 'positive'} #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `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`: 0.0001 - `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`: 0.0 - `warmup_steps`: 10 - `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 - `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`: 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} - `parallelism_config`: 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 - `project`: huggingface - `trackio_space_id`: trackio - `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`: None - `hub_always_push`: False - `hub_revision`: None - `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 - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: no - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: True - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {'query': 'anchor', 'document': 'positive'} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Validation Loss | val_set_fine_cosine_ndcg@10 | |:----------:|:------:|:---------------:|:---------------------------:| | 0.0125 | 10 | 0.8461 | 0.7841 | | 0.0251 | 20 | 0.8195 | 0.8009 | | 0.0376 | 30 | 0.7884 | 0.7967 | | 0.0501 | 40 | 0.7641 | 0.8097 | | **0.0627** | **50** | **0.7503** | **0.8146** | | 0.0752 | 60 | 0.7140 | 0.8151 | | 0.0877 | 70 | 0.7165 | 0.8180 | | 0.1003 | 80 | 0.6955 | 0.8131 | | 0.1128 | 90 | 0.6866 | 0.8157 | | 0.1253 | 100 | 0.6735 | 0.8170 | | 0.1379 | 110 | 0.6766 | 0.8159 | | 0.1504 | 120 | 0.6609 | 0.8161 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.12.12 - Sentence Transformers: 5.2.2 - Transformers: 4.57.1 - PyTorch: 2.8.0+cu126 - Accelerate: 1.11.0 - Datasets: 4.4.2 - Tokenizers: 0.22.1 ## 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", } ``` #### SpladeLoss ```bibtex @misc{formal2022distillationhardnegativesampling, title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective}, author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant}, year={2022}, eprint={2205.04733}, archivePrefix={arXiv}, primaryClass={cs.IR}, url={https://arxiv.org/abs/2205.04733}, } ``` #### SparseMultipleNegativesRankingLoss ```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} } ``` #### FlopsLoss ```bibtex @article{paria2020minimizing, title={Minimizing flops to learn efficient sparse representations}, author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s}, journal={arXiv preprint arXiv:2004.05665}, year={2020} } ```