---
language: []
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dataset_size:n<1K
- loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
- source_sentence: What is the benefit of using a box plot?
sentences:
- Why would you choose a box plot over a bar chart?
- Can you explain the difference between line charts and bar charts?
- What does color and size represent in Heat Map visualization?
- source_sentence: Can you explain how to read a bar chart?
sentences:
- Can you explain how to read a line chart?
- Can you explain the difference between line charts and bar charts?
- Why are heatmaps often used for representing correlation matrices?
- source_sentence: What is a heatmap and when is it useful?
sentences:
- What is a heatmap and in what situations is it useful?
- Why should one consider using radar charts for data representation?
- Bar charts are best suited for representing categorical data or comparing discrete
groups. This includes data like different groups' scores, frequency of categories,
or changes over a period of time for different categories.
- source_sentence: Can you explain how to read a line chart?
sentences:
- Can you explain how to interpret a line chart?
- Can you define data visualization and its importance in businesses?
- Why are heatmaps often used for representing correlation matrices?
- source_sentence: What make a data visualization effective?
sentences:
- What are the key principles in creating effective data visualizations?
- In what situation would you use a bar chart for data visualization?
- A bar chart represents data in rectangular bars with lengths proportional to the
values that they represent. It is commonly used to compare individual data points
with each other. On the other hand, a line chart uses lines to connect individual
data points and shows trends over a period of time.
pipeline_tag: sentence-similarity
---
# 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). 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
### 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("edubm/vis-sim-a2a-mpnet")
# Run inference
sentences = [
'What make a data visualization effective?',
'What are the key principles in creating effective data visualizations?',
'In what situation would you use a bar chart for data visualization?',
]
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
#### Unnamed Dataset
* Size: 380 training samples
* Columns: Question and Answer
* Approximate statistics based on the first 1000 samples:
| | Question | Answer |
|:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 8 tokens
- mean: 14.96 tokens
- max: 23 tokens
| - min: 19 tokens
- mean: 95.53 tokens
- max: 118 tokens
|
* Samples:
| Question | Answer |
|:------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| How do you interpret a line chart? | A line chart is interpreted by observing the plotted data points that are connected by a line, representing series of data over a certain period. The x-axis typically denotes time or categories, while the y-axis represents the quantity of what is being measured. An upward trend of the line indicates an increase and a downward trend indicates a decrease in the data's value. The steeper the line, the more rapid the increase or decrease. Multiple lines on the same graph can indicate comparisons between different datasets. Further, |
| Can you define a heatmap in data visualization? | A heatmap in data visualization is a graphical representation of data where individual values contained in a matrix or data table are represented as colors. It provides an overview of the data and makes complex data sets understandable and visually appealing. Heatmaps are often used to visualize correlation matrices, geographical data, or the behavior of website visitors, among other aspects. |
| What are radar charts, and what kind of data are they useful for displaying? | Radar charts, also known as spider or web charts, are graphical representations used in data analysis for displaying multivariate data in the form of two-dimensional charts. These charts are effectively used to visualize the performance or rating data, especially for comparing multiple entities based on different parameters. They can also highlight the contrast between targeted and achieved performance.
The values each variable takes are plotted on its individual axes that start from the center of the chart. All these axes are arranged radially, which gives the chart a |
* 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