--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:222635 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: sentence-transformers/all-MiniLM-L6-v2 widget: - source_sentence: OMBRELLAS sentences: - '''ALPHASORT, to sort into alphabetic order [v]''' - '''OMBRELLA, an umbrella [n]''' - '''PHYLLID, the leaf of a liverwort or moss [n]''' - source_sentence: ROUNCE sentences: - '''LYMPHADENITIS, inflammation of the lymph nodes [n]''' - '''one who advocates curialism, the system of government of curia [n -S]''' - '''part of a hand printing press [n -S]''' - source_sentence: SEROON sentences: - '''(Spanish) a crate or hamper; a bale wrapped in hide, also CEROON, SERON [n -S]''' - '''a white crystalline soluble phenol used as a photographic developer [n -S]''' - '''serving to disseminate [adj]''' - source_sentence: BLAFF sentences: - '''to bark [v -ED, -ING, -S]''' - '''RAZORCLAM, a lamellibranch mollusc with a shell like an old-fashioned razor handle, also RAZORFISH [n]''' - '''HYPERCORRECT, refers to a linguistic construction or pronunciation produced by mistaken analogy with standard usage out of a desire to be correct, such as "open widely" or "on behalf of my wife and I" [adv]''' - source_sentence: TRAUMATOLOGY sentences: - '''FELLATRIX, a female who fellates [n]''' - '''pertaining to a grandparent [adj]''' - '''the study of wounds and their effects [n TRAUMATOLOGIES]''' pipeline_tag: sentence-similarity 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 model-index: - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 results: - task: type: information-retrieval name: Information Retrieval dataset: name: dictionary test type: dictionary-test metrics: - type: cosine_accuracy@1 value: 0.6825254231197672 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8121384167594955 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.831147364260304 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.850587516619354 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.6825254231197672 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.27071280558649846 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1662294728520608 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08505875166193541 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.6825254231197672 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8121384167594955 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.831147364260304 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.850587516619354 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7750717041193917 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.7499954655044675 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.7522443165977887 name: Cosine Map@100 --- # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the csv dataset. 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) - **Maximum Sequence Length:** 256 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - csv ### 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': 256, '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}) (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("mehularora/scrabble-embed-v2") # Run inference sentences = [ 'TRAUMATOLOGY', "'the study of wounds and their effects [n TRAUMATOLOGIES]'", "'FELLATRIX, a female who fellates [n]'", ] 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, 0.7472, 0.0801], # [0.7472, 1.0000, 0.2525], # [0.0801, 0.2525, 1.0000]]) ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `dictionary-test` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.6825 | | cosine_accuracy@3 | 0.8121 | | cosine_accuracy@5 | 0.8311 | | cosine_accuracy@10 | 0.8506 | | cosine_precision@1 | 0.6825 | | cosine_precision@3 | 0.2707 | | cosine_precision@5 | 0.1662 | | cosine_precision@10 | 0.0851 | | cosine_recall@1 | 0.6825 | | cosine_recall@3 | 0.8121 | | cosine_recall@5 | 0.8311 | | cosine_recall@10 | 0.8506 | | **cosine_ndcg@10** | **0.7751** | | cosine_mrr@10 | 0.75 | | cosine_map@100 | 0.7522 | ## Training Details ### Training Dataset #### csv * Dataset: csv * Size: 222,635 training samples * Columns: word and definition * Approximate statistics based on the first 1000 samples: | | word | definition | |:--------|:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | word | definition | |:-------------------------|:------------------------------------------------------------------------------------| | LICHGATES | 'LICHGATE, the roofed gate of a churchyard, also LYCHGATE [n]' | | MOULDING | 'a long, narrow strip used to decorate a surface, also MOLDING [n -S]' | | PARABAPTISM | 'uncanonical baptism [n -S]' | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 384, 256 ], "matryoshka_weights": [ 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `fp16`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 8 - `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`: 0.0 - `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 - `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`: 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} - `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`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | dictionary-test_cosine_ndcg@10 | |:------:|:----:|:-------------:|:------------------------------:| | 0.0287 | 100 | 1.0186 | 0.7180 | | 0.0575 | 200 | 0.7633 | 0.7274 | | 0.0862 | 300 | 0.75 | 0.7398 | | 0.1150 | 400 | 0.7503 | 0.7456 | | 0.1437 | 500 | 0.7271 | 0.7496 | | 0.1725 | 600 | 0.6531 | 0.7508 | | 0.2012 | 700 | 0.6586 | 0.7560 | | 0.2300 | 800 | 0.6559 | 0.7591 | | 0.2587 | 900 | 0.6116 | 0.7572 | | 0.2874 | 1000 | 0.615 | 0.7625 | | 0.3162 | 1100 | 0.5926 | 0.7596 | | 0.3449 | 1200 | 0.6414 | 0.7623 | | 0.3737 | 1300 | 0.6143 | 0.7641 | | 0.4024 | 1400 | 0.6464 | 0.7655 | | 0.4312 | 1500 | 0.6039 | 0.7676 | | 0.4599 | 1600 | 0.514 | 0.7643 | | 0.4886 | 1700 | 0.5719 | 0.7675 | | 0.5174 | 1800 | 0.612 | 0.7675 | | 0.5461 | 1900 | 0.5639 | 0.7698 | | 0.5749 | 2000 | 0.6025 | 0.7672 | | 0.6036 | 2100 | 0.5623 | 0.7719 | | 0.6324 | 2200 | 0.5484 | 0.7698 | | 0.6611 | 2300 | 0.5799 | 0.7730 | | 0.6899 | 2400 | 0.5253 | 0.7716 | | 0.7186 | 2500 | 0.5134 | 0.7732 | | 0.7473 | 2600 | 0.5543 | 0.7721 | | 0.7761 | 2700 | 0.5342 | 0.7736 | | 0.8048 | 2800 | 0.5507 | 0.7746 | | 0.8336 | 2900 | 0.5176 | 0.7737 | | 0.8623 | 3000 | 0.5067 | 0.7751 | | 0.8911 | 3100 | 0.548 | 0.7749 | | 0.9198 | 3200 | 0.5443 | 0.7751 | | 0.9485 | 3300 | 0.5603 | 0.7751 | | 0.9773 | 3400 | 0.5774 | 0.7751 | ### Framework Versions - Python: 3.11.4 - Sentence Transformers: 5.1.2 - Transformers: 4.57.3 - PyTorch: 2.9.1+cpu - Accelerate: 1.12.0 - Datasets: 4.4.1 - 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", } ``` #### 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} } ```