---
base_model: sentence-transformers/all-mpnet-base-v2
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/all-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the train 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
- **Maximum Sequence Length:** 384 tokens
- **Output Dimensionality:** 768 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
(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("anomys/gsm-finetunned-v2")
# 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, 768]
# 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 | - min: 12 tokens
- mean: 15.57 tokens
- max: 26 tokens
| - min: 9 tokens
- mean: 33.72 tokens
- max: 82 tokens
|
* 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 | - min: 12 tokens
- mean: 15.45 tokens
- max: 26 tokens
| - min: 9 tokens
- mean: 33.56 tokens
- max: 82 tokens
|
* 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