---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:44114
- loss:ContrastiveLoss
widget:
- source_sentence: The city is located in 1889 , along the Nehalem River and Nehalem
Bay , near the Pacific Ocean .
sentences:
- Incorporated in 1889 , the city lies along the Pacific Ocean near the Nehalem
River and Nehalem Bay .
- Along the coast there are almost 2,000 islands , about three quarters of which
are uninhabited .
- The mammalian fauna of Madagascar is largely endemic and highly distinctive .
- source_sentence: Chris Blackwell , the mother of Blackwell , was one of the greatest
landowners in Saint Mary at the turn of the 20th century .
sentences:
- One of the largest landowners in Saint Mary at the turn of the twentieth century
was Blanche Blackwell , mother of Chris Blackwell .
- The cast for the third season of `` California Dreams '' was the same as the cast
for the fourth season .
- 'The affine scaling direction can be used to define a heuristic to adaptively
the centering parameter as :'
- source_sentence: The Roman - Catholic diocese of Cyangugu is a diocese in the city
of Cyangugu in the church province of Kigali , Rwanda .
sentences:
- Chad Ochocinco ( born 1978 ; formerly Chad Johnson ) is an American - American
- football receiver .
- She published several jingles and sang some successful music videos .
- The Roman Catholic Diocese of Cyangugu is a diocese located in the city of Kigali
in the ecclesiastical province of Cyangugu in Rwanda .
- source_sentence: Abhishek introduces Rishi and Netra Tanuja as his wife .
sentences:
- Abhishek introduces Tanuja to Rishi and Netra as his wife .
- At the end of the 18th century the castle was property of the Counts Ansidei ,
in the 19th century it was bought by the Piceller family .
- Deepaaradhana is an Indian Malayalam film of 1983 , produced by Vijayanand and
directed by TK Balachandran .
- source_sentence: He is also well singing in other regional forms such as Bhajans
, Ghazals , Nazrulgeeti and numerous semi-classical songs .
sentences:
- When the membrane potential reaches approximately – 60 mV , the K channels close
and the Na channels open and the prepotential phase begins again .
- He is also skilled in singing other regional forms like Bhajans , Ghazals , Nazrulgeeti
and numerous semi-classical songs as well .
- Conotalopia mustelina is a species of sea snail , a top gastropod mollusk in the
Trochidae family , the navy snails .
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy
- cosine_accuracy_threshold
- cosine_f1
- cosine_f1_threshold
- cosine_precision
- cosine_recall
- cosine_ap
- cosine_mcc
model-index:
- name: SentenceTransformer
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: paws val watcher
type: paws-val-watcher
metrics:
- type: cosine_accuracy
value: 0.9277327935222672
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.8190367221832275
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9206490331184708
name: Cosine F1
- type: cosine_f1_threshold
value: 0.8180307745933533
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.8942141623488774
name: Cosine Precision
- type: cosine_recall
value: 0.9486944571690334
name: Cosine Recall
- type: cosine_ap
value: 0.9612681828396534
name: Cosine Ap
- type: cosine_mcc
value: 0.8556704322534656
name: Cosine Mcc
---
# SentenceTransformer
This is a [sentence-transformers](https://www.SBERT.net) model trained. 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
- **Maximum Sequence Length:** 64 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
### 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': 64, 'do_lower_case': False, 'architecture': 'BertModel'})
(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})
)
```
## 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("sentence_transformers_model_id")
# Run inference
sentences = [
'He is also well singing in other regional forms such as Bhajans , Ghazals , Nazrulgeeti and numerous semi-classical songs .',
'He is also skilled in singing other regional forms like Bhajans , Ghazals , Nazrulgeeti and numerous semi-classical songs as well .',
'Conotalopia mustelina is a species of sea snail , a top gastropod mollusk in the Trochidae family , the navy snails .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9958, 0.5938],
# [0.9958, 1.0000, 0.6041],
# [0.5938, 0.6041, 1.0000]])
```
## Evaluation
### Metrics
#### Binary Classification
* Dataset: `paws-val-watcher`
* Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:--------------------------|:-----------|
| cosine_accuracy | 0.9277 |
| cosine_accuracy_threshold | 0.819 |
| cosine_f1 | 0.9206 |
| cosine_f1_threshold | 0.818 |
| cosine_precision | 0.8942 |
| cosine_recall | 0.9487 |
| **cosine_ap** | **0.9613** |
| cosine_mcc | 0.8557 |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 44,114 training samples
* Columns: sentence_0, sentence_1, and label
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | label |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | - min: 12 tokens
- mean: 26.76 tokens
- max: 54 tokens
| - min: 11 tokens
- mean: 26.82 tokens
- max: 54 tokens
| - min: 0.0
- mean: 0.49
- max: 1.0
|
* Samples:
| sentence_0 | sentence_1 | label |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
| The southern area contains the Tara Mountains and the northern area consists of open plains along the coast , and the city proper . | The southern area contains the Tara mountains and the northern area consists of open plains along the coast and the actual city . | 1.0 |
| It began as a fishing village inhabited by Polish settlers from the Kaszub region in 1870 , as well as by some German immigrants . | It began as a fishing village populated by German settlers from the Kaszub region , as well as some Polish immigrants in 1870 . | 0.0 |
| Wyoming Highway 377 was a short Wyoming state road in central Sweetwater County that served the community of Point of Rocks and the Jim Bridger Power Plant . | Wyoming Highway 377 was a short Wyoming State Road in central Sweetwater County that served as the community of Point of Rocks and the Jim Bridger Power Plant . | 1.0 |
* Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
```json
{
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
"margin": 0.5,
"size_average": true
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 4
- `multi_dataset_batch_sampler`: round_robin
#### 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
- `torch_empty_cache_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
- `num_train_epochs`: 4
- `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`: False
- `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`: round_robin
- `router_mapping`: {}
- `learning_rate_mapping`: {}