--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:12800 - loss:MultipleNegativesRankingLoss base_model: microsoft/MiniLM-L12-H384-uncased widget: - source_sentence: Two boys are playing in pool filled with sparkling blue water. sentences: - A boy plays in the pool. - Woman holds her purse. - The child is very brave to hold onto that tail. - source_sentence: An artist shows off his work to a large crowd of people who appear to be listening intently to the artist's description of his display. sentences: - A man with a bike watched musicians playing. - A piece of art on display. - A man is climbing. - source_sentence: A man on a street in a bright t-shirt holds some sort of tablet towards a woman in a pink t-shirt and shades. sentences: - The man is working on a sculpture. - Older men are sitting. - A woman is shown a tablet by a man standing on the street. - source_sentence: A skateboarder is riding a skateboard along a metal railing in front of a concrete building. sentences: - A man is dressed in traditional Jewish clothing. - A man has some flowers. - A skateboarder is riding a skateboard - source_sentence: Three women enjoying a balloon joyride. sentences: - The group of people had braided hair. - Three women are on a balloon ride. - A woman who is wearing purple is painting another woman. pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on microsoft/MiniLM-L12-H384-uncased This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased). It maps sentences & paragraphs to a 384-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:** [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 384 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': 512, 'do_lower_case': False, 'architecture': 'BertModel'}) (1): Pooling({'word_embedding_dimension': 384, '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("Borsa356/bert_mnr_7") # Run inference sentences = [ 'Three women enjoying a balloon joyride.', 'Three women are on a balloon ride.', 'A woman who is wearing purple is painting another woman.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.8457, 0.2791], # [0.8457, 1.0000, 0.3065], # [0.2791, 0.3065, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 12,800 training samples * Columns: sentence_0 and sentence_1 * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence_0 | sentence_1 | |:------------------------------------------------------------------------------------------------|:--------------------------------------------------------------| | A classroom of students discussing lecture. | A classroom is discussing the topics of the day. | | A overweight man with shorts on about to get on a motorcycle. | A chubby man gets ready to go for a ride. | | A woman stares at something lighted that three people are holding in front of her. | A woman is staring. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `num_train_epochs`: 2 - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `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`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 2 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `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`: False - `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`: 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`: 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`: False - `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`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: round_robin - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | |:-----:|:----:|:-------------:| | 1.25 | 500 | 0.7044 | ### Framework Versions - Python: 3.13.5 - Sentence Transformers: 5.0.0 - Transformers: 4.53.0 - PyTorch: 2.7.1+cpu - Accelerate: 1.8.1 - Datasets: 3.6.0 - Tokenizers: 0.21.2 ## 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", } ``` #### 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} } ```