--- base_model: sentence-transformers/multi-qa-MiniLM-L6-cos-v1 datasets: [] language: [] library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:2160 - loss:MultipleNegativesRankingLoss widget: - source_sentence: Are there any special events for kids? (variation 72) sentences: - No, pets are not allowed. - Yes, there are special events for kids like the Love-themed Movie Night on February 17 and Sunday Family Picnic on March 18. - The mall's address is Miyapur Main Rd, ICRISAT Colony, Madeenaguda, Hyderabad, Telangana 500050 - source_sentence: Who built the chatbot? (variation 16) sentences: - Most stores accept cash, credit cards, debit cards, and UPI payments. Individual stores may have additional payment options. - The chatbot was built by KreativeChat. Their contact information is support@kreativechat.com. - Yes, there is a Valentine's Day Dinner event on February 14, 2024, from 7:00 PM to 10:00 PM at the Rooftop Restaurant. - source_sentence: Where can I find details about the Weekend Jazz Brunch? (variation 100) sentences: - Our mall chatbot is your primary source for information and assistance. For specific inquiries or to meet with mall management, please visit the 6th-floor mall management front desk. - The Weekend Jazz Brunch takes place at the Jazz Cafe on February 18, 2024, from 11:00 AM to 2:00 PM. - Washrooms are conveniently located on each floor. Ask our chatbot for a floor plan with marked washrooms. - source_sentence: Is there a Lost and Found section in the mall? (variation 1) sentences: - No, charging points are not available in the mall. - Yes, there is a Valentine's Day Dinner event on February 14, 2024, from 7:00 PM to 10:00 PM at the Rooftop Restaurant. - 'Yes, there is. Please fill out this Google Form: [https://forms.gle/7R9rW1xamhktqBXh9]' - source_sentence: Where are the washrooms located? (variation 95) sentences: - The chatbot was built by KreativeChat. Their contact information is support@kreativechat.com. - No, there are no information desks or customer desks. For inquiries, please leave a message or ask the chatbot. The relevant person will respond accordingly. - Washrooms are conveniently located on each floor. Ask our chatbot for a floor plan with marked washrooms. --- # SentenceTransformer based on sentence-transformers/multi-qa-MiniLM-L6-cos-v1 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-MiniLM-L6-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1) on the train 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/multi-qa-MiniLM-L6-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 384 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - train ### 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: 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("anomys/gsm-finetunned-v3") # Run inference sentences = [ 'Where are the washrooms located? (variation 95)', 'Washrooms are conveniently located on each floor. Ask our chatbot for a floor plan with marked washrooms.', 'The chatbot was built by KreativeChat. Their contact information is support@kreativechat.com.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Training Details ### Training Dataset #### train * Dataset: train * Size: 2,160 training samples * Columns: question and response * Approximate statistics based on the first 1000 samples: | | question | response | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | question | response | |:-----------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------| | Is there public WiFi available in the mall? (variation 4) | Sorry, no WiFi is available for the public. | | What are the special promotions available? (variation 65) | Special promotions include up to 50% off at Reliance Trends, 20% off new arrivals at Style Union, and more. | | What are the mall hours of operation? (variation 47) | GSM Mall & Multiplex is open from 11:00 AM to 10:00 PM on weekdays and weekends. Individual store timings may vary. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### train * Dataset: train * Size: 540 evaluation samples * Columns: question and response * Approximate statistics based on the first 1000 samples: | | question | response | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | question | response | |:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------| | What offers are available at the food court? (variation 12) | Offers at the food court include Buy One Get One Half Off Shakes at Thick Shake Factory, Taco Tuesday Special at California Burrito, and more. | | What is the date and time for the Spring Fashion Show? (variation 14) | The Spring Fashion Show is on March 24, 2024, from 6:00 PM to 8:00 PM at the Mall Runway. | | Where is GSM Mall & Multiplex located? (variation 30) | The mall's address is Miyapur Main Rd, ICRISAT Colony, Madeenaguda, Hyderabad, Telangana 500050 | * 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 - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `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`: 5e-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`: 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 - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | train loss | |:------:|:----:|:-------------:|:----------:| | 0.3704 | 50 | 0.087 | 0.0000 | | 0.7407 | 100 | 0.0001 | 0.0000 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.0.1 - Transformers: 4.41.2 - PyTorch: 2.3.0+cu121 - Accelerate: 0.32.1 - Datasets: 2.20.0 - 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", } ``` #### 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} } ```