--- base_model: intfloat/multilingual-e5-base datasets: [] language: [] library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:100 - loss:TripletLoss widget: - source_sentence: How many athletes from region 151 have won a medal? sentences: - athletes refer to person_id; region 151 refers to region_id = 151; won a medal refers to medal_id <> 4; - Rio de Janeiro refers to city_name = 'Rio de Janeiro'; - the highest number of participants refers to MAX(COUNT(person_id)); the lowest number of participants refers to MIN(COUNT(person_id)); Which summer Olympic refers to games_name where season = 'Summer'; - source_sentence: What is the id of Rio de Janeiro? sentences: - year refers to games_year; - athletes refer to person_id; region 151 refers to region_id = 151; won a medal refers to medal_id <> 4; - Rio de Janeiro refers to city_name = 'Rio de Janeiro'; - source_sentence: Please list the Asian populations of all the residential areas with the bad alias "URB San Joaquin". sentences: - '"URB San Joaquin" is the bad_alias' - name of congressman implies full name which refers to first_name, last_name; Guanica is the city; - '"URB San Joaquin" is the bad_alias' - source_sentence: State the male population for all zip code which were under the Berlin, NH CBSA. sentences: - '"Berlin, NH" is the CBSA_name' - '"Barre, VT" is the CBSA_name' - representative's full names refer to first_name, last_name; area which has highest population in 2020 refers to MAX(population_2020); - source_sentence: Which state has the most bad aliases? sentences: - '"York" is the city; ''ME'' is the state; type refers to CBSA_type' - the most bad aliases refer to MAX(COUNT(bad_alias)); - precise location refers to latitude, longitude --- # SentenceTransformer based on intfloat/multilingual-e5-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the train and test datasets. 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:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Datasets:** - train - test ### 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}) with Transformer model: XLMRobertaModel (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): 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("DariaaaS/e5-args-1") # Run inference sentences = [ 'Which state has the most bad aliases?', 'the most bad aliases refer to MAX(COUNT(bad_alias));', 'precise location refers to latitude, longitude', ] 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] ``` ## Training Details ### Training Datasets #### train * Dataset: train * Size: 80 training samples * Columns: query, positive, and negative * Approximate statistics based on the first 1000 samples: | | query | positive | negative | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | query | positive | negative | |:-----------------------------------------------------|:------------------------------------------|:--------------------------------------------------------------------------------------------------------| | How many zip codes are under Barre, VT? | "Barre, VT" is the CBSA_name | coordinates refers to latitude, longitude; latitude = '18.090875; longitude = '-66.867756' | | How many zip codes are under Barre, VT? | "Barre, VT" is the CBSA_name | name of county refers to county | | How many zip codes are under Barre, VT? | "Barre, VT" is the CBSA_name | median age over 40 refers to median_age > 40 | * Loss: [TripletLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters: ```json { "distance_metric": "TripletDistanceMetric.EUCLIDEAN", "triplet_margin": 5 } ``` #### test * Dataset: test * Size: 20 training samples * Columns: query, positive, and negative * Approximate statistics based on the first 1000 samples: | | query | positive | negative | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | query | positive | negative | |:---------------------------------------------------------|:-------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------| | Where is competitor Estelle Nze Minko from? | Where competitor is from refers to region_name; | NOC code refers to noc; the heaviest refers to MAX(weight); | | Where is competitor Estelle Nze Minko from? | Where competitor is from refers to region_name; | host city refers to city_name; the 1968 Winter Olympic Games refer to games_name = '1968 Winter'; | | Where is competitor Estelle Nze Minko from? | Where competitor is from refers to region_name; | the gold medal refers to medal_name = 'Gold'; | * Loss: [TripletLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters: ```json { "distance_metric": "TripletDistanceMetric.EUCLIDEAN", "triplet_margin": 5 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `warmup_ratio`: 0.1 - `fp16`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `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`: 1 - `eval_accumulation_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`: 4 - `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`: 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`: 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 - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.42.4 - PyTorch: 2.4.0+cu121 - Accelerate: 0.32.1 - Datasets: 2.21.0 - 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", } ``` #### TripletLoss ```bibtex @misc{hermans2017defense, title={In Defense of the Triplet Loss for Person Re-Identification}, author={Alexander Hermans and Lucas Beyer and Bastian Leibe}, year={2017}, eprint={1703.07737}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```