---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:116941
- loss:SoftmaxLoss
base_model: google-bert/bert-base-cased
widget:
- source_sentence: O[C@@H]1CC(CCc2c(O)cc(Cl)cc2Cl)OC(=O)C1
sentences:
- O[C@@H]1C[C@@H](CC[C@@H]2CCC[C@@H]3CCCC[C@H]23)OC(=O)C1
- O[C@@H]1CC(CCc2cccc3ccccc23)OC(=O)C1
- CC(C)n1c(CC[C@@H](O)C[C@@H](O)CC([O-])=O)c(c(c1C(=O)NCc1ccccc1)-c1ccccn1)-c1ccc(F)cc1
- source_sentence: O[C@@H]1C[C@H](OC(=O)C1)\C=C\c1cnc2c(Sc3ccc(F)cc3)c(Sc3ccc(F)cc3)c(F)cc2c1Sc1ccc(F)cc1
sentences:
- O[C@H](C[C@H](O)\C=C\c1c2CCCc2nn1-c1ccc(F)cc1)CC([O-])=O
- C[C@H](CC\C=C(/C)C(O)=O)[C@H]1C[C@H](O)[C@@]2(C)C3=CC[C@H]4C(C)(C)C(=O)CC[C@]4(C)C3=CC[C@]12C
- CC(C)c1ccc(Sc2c(\C=C\[C@@H]3C[C@@H](O)CC(=O)O3)cnc3cc(Cl)c(F)cc23)cc1
- source_sentence: O[C@H](C[C@H](O)\C=C\c1c2CCCCc2nn1-c1ccc(F)cc1)CC([O-])=O
sentences:
- O[C@@H]1C[C@H](OC(=O)C1)\C=C\c1cnc2cc(Sc3ccccc3)c(Sc3ccccc3)cc2c1Sc1ccccc1
- CC[C@H](C)[C@H](N)C(=O)N[C@@H](C)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CCC(O)=O)C(O)=O
- CC(C)n1c(CC[C@@H](O)C[C@@H](O)CC(O)=O)c(c(c1C(=O)N(C)Cc1ccccc1)-c1ccccc1)-c1ccc(F)cc1
- source_sentence: COc1ccc(CNC(=O)c2nc(-c3ccc(F)cc3)n(CC[C@@H](O)C[C@@H](O)CC([O-])=O)c2C2CC2)cc1
sentences:
- CC(C)c1nc(nc(-c2ccc(F)cc2)c1\C=C\[C@@H](O)C[C@@H](O)CC(O)=O)N(c1nnnn1C)S(C)(=O)=O
- CC(C)c1c(CC[C@@H](O)C[C@@H](O)CC(O)=O)n(nc1C(=O)N(C)Cc1ccccc1)-c1ccc(F)cc1
- Cc1c(OCC(O)C[C@@H](O)CC([O-])=O)c(cc2ccccc12)C(c1ccc(F)cc1)c1ccc(F)cc1
- source_sentence: CC(C)n1c(CC[C@@H](O)C[C@@H](O)CC([O-])=O)c(c(c1C(=O)NCc1cccc(c1)C(N)=O)-c1ccccc1)-c1ccc(F)cc1
sentences:
- CC(C)c1nc(c(-c2ccc(F)cc2)n1\C=C\[C@@H](O)C[C@@H](O)CC(O)=O)-c1ccc(F)cc1
- CCn1nnc(n1)C(\C=C\[C@@H](O)C[C@@H](O)CC([O-])=O)=C(c1ccc(F)cc1)c1ccc(F)cc1
- CC(C)c1nc(nc(-c2ccc(F)cc2)c1\C=C\[C@@H](O)C[C@@H](O)CC(O)=O)N(C)c1ccnn1C
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on google-bert/bert-base-cased
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the csv 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:** [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- csv
### 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, '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("cafierom/905_Statin_Contrastive")
# Run inference
sentences = [
'CC(C)n1c(CC[C@@H](O)C[C@@H](O)CC([O-])=O)c(c(c1C(=O)NCc1cccc(c1)C(N)=O)-c1ccccc1)-c1ccc(F)cc1',
'CC(C)c1nc(c(-c2ccc(F)cc2)n1\\C=C\\[C@@H](O)C[C@@H](O)CC(O)=O)-c1ccc(F)cc1',
'CCn1nnc(n1)C(\\C=C\\[C@@H](O)C[C@@H](O)CC([O-])=O)=C(c1ccc(F)cc1)c1ccc(F)cc1',
]
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, 0.9994, -0.0483],
# [ 0.9994, 1.0000, -0.0453],
# [-0.0483, -0.0453, 1.0000]])
```
## Training Details
### Training Dataset
#### csv
* Dataset: csv
* Size: 116,941 training samples
* Columns: premise, hypothesis, and label
* Approximate statistics based on the first 1000 samples:
| | premise | hypothesis | label |
|:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details |
CC[C@H](C)C(=O)O[C@H]1C[C@@H](C)C[C@@H]2C=C[C@H](C)[C@H](CCC(O)C[C@@H](O)CC(O)=O)C12 | CCCCCCCCCCCCCCCC1(O)CCOC(O)C1 | 2 |
| O[C@H](C[C@H](O)\C=C\c1c(Cl)cc(Cl)cc1-c1ccc(F)cc1)CC([O-])=O | C[C@@]1(O)C[C@H](OC(=O)C1)\C=C\c1ccc(Cl)cc1Cl | 2 |
| CC(C)c1nc(nc(-c2ccc(F)cc2)c1\C=C\[C@@H]1C[C@@H](O)CC(=O)O1)-c1ccc(F)cc1 | CC(C)C[C@H](NC(=O)CN)C(=O)N1CCC[C@H]1C(=O)N[C@@H](CCC(O)=O)C(=O)NCC(=O)NCC(O)=O | 2 |
* Loss: [SoftmaxLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
### Evaluation Dataset
#### csv
* Dataset: csv
* Size: 20,637 evaluation samples
* Columns: premise, hypothesis, and label
* Approximate statistics based on the first 1000 samples:
| | premise | hypothesis | label |
|:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | COC(=O)C[C@H](O)C[C@H](O)\C=C\n1c(C(C)C)c(Br)c(c1-c1ccc(F)cc1)-c1ccc(F)cc1 | C[C@H](CC(O)CC(O)CC([O-])=O)[C@H]1CC[C@H]2[C@@H]3[C@@H](C[C@@H]4C[C@@H](CC[C@]4(C)[C@H]3C[C@H](OC(C)=O)[C@]12C)OC(C)=O)OC(C)=O | 2 |
| CC(C)n1c(CC[C@@H](O)C[C@@H](O)CC([O-])=O)c(c(c1C(=O)Nc1ccc(O)cc1)-c1ccccc1)-c1ccc(F)cc1 | CC[C@H](C)C(=O)O[C@H]1C[C@H](C)C=C2C=C[C@H](C)[C@H](CC[C@@H]3C[C@@H](O)CC(=O)O3)[C@@H]12 | 0 |
| CC(C)C(=O)O[C@H]1C[C@@H](C)C=C2C=C[C@H](C)[C@H](CC[C@@H]3C[C@@H](O)CC(=O)O3)C12 | CC(C)c1c(nc(-c2ccc(F)cc2)n1\C=C\[C@@H](O)C[C@@H](O)CC([O-])=O)-c1ccc(F)cc1 | 0 |
* Loss: [SoftmaxLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `weight_decay`: 0.01
- `num_train_epochs`: 10
- `warmup_steps`: 100
- `fp16`: True
#### All Hyperparameters