This is a sentence-transformers model finetuned from DeepChem/ChemBERTa-77M-MLM. 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: DeepChem/ChemBERTa-77M-MLM
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

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("HassanCS/chemberta-clintox-tunned-3")
# Run inference
sentences = [
    'C[NH+](C)CCc1c[nH]c2ccc(Cn3cncn3)cc12',
    'C[N+]12CCC(CC1)C(OC(=O)C(O)(c1ccccc1)c1ccccc1)C2',
    'CC12CCCCCC(Cc3ccc(O)cc31)C2[NH3+]',
]
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]

Evaluation

Metrics

Binary Classification

Dataset: all-dev
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.5344
cosine_accuracy_threshold	0.6344
cosine_f1	0.6761
cosine_f1_threshold	0.57
cosine_precision	0.5149
cosine_recall	0.9843
cosine_ap	0.4791
cosine_mcc	0.0755

Training Details

Training Dataset

Unnamed Dataset

Size: 4,000 training samples
Columns: smiles1, smiles2, and label
Approximate statistics based on the first 1000 samples:
smiles1 smiles2 label
type string string int
details
min: 3 tokens
mean: 46.57 tokens
max: 221 tokens
min: 3 tokens
mean: 54.2 tokens
max: 221 tokens
0: ~49.40%
1: ~50.60%

Samples:

smiles1	smiles2	label
`C=C1CCC(O)CC1=CC=C1CCCC2(C)C1CCC2C(C)C=CC(C)C(C)C`	`CCCCCc1cc(O)c2c(c1)OC(C)(C)C1CCC(C)=CC21`	`1`
`CNC1=[NH+]c2ccc(Cl)cc2C(c2ccccc2)=[object Object]C1`	`O=C1CCC(N2C(=O)c3ccccc3C2=O)C(=O)N1`	`0`
`CC(=O)Oc1c(C)c(C)c2c(c1C)CCC(C)(CCCC(C)CCCC(C)CCCC(C)C)O2`	`Nc1nc(Cl)nc2c1ncn2C1OC(CO)C(O)C1F`	`0`

Loss: ContrastiveLoss with these parameters:
json
1{ 2 "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", 3 "margin": 0.5, 4 "size_average": true 5}

Evaluation Dataset

Unnamed Dataset

Size: 2,008 evaluation samples
Columns: smiles1, smiles2, and label
Approximate statistics based on the first 1000 samples:
smiles1 smiles2 label
type string string int
details
min: 18 tokens
mean: 56.98 tokens
max: 244 tokens
min: 18 tokens
mean: 65.99 tokens
max: 244 tokens
0: ~47.90%
1: ~52.10%

Samples:

smiles1	smiles2	label
`CC(C)(C)NC(=O)C1CC2CCCCC2C[NH+]1CC(O)C(Cc1ccccc1)NC(=O)C(CC(N)=O)NC(=O)c1ccc2ccccc2n1`	`C[object Object]CCc1c[nH]c2ccc(Cn3cncn3)cc12`	`1`
`CC12CC(=C[O-])C(=O)CC1CCC1C2CCC2(C)C1CCC2(C)O`	`CC(C)C1(C(=O)NC2CC(=O)OC2(O)CF)CC(c2nccc3ccccc23)=NO1`	`0`
`CC12CCCCCC(Cc3ccc(O)cc31)C2[NH3+]`	`C[NH2+]C1C(O)C([NH2+]C)C2OC3(O)C(=O)CC(C)OC3OC2C1O`	`1`

Loss: ContrastiveLoss with these parameters:
json
1{ 2 "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", 3 "margin": 0.5, 4 "size_average": true 5}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 1e-05
weight_decay: 0.01
num_train_epochs: 5
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
hub_model_id: HassanCS/chemberta-clintox-tunned-3
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: 32
per_device_eval_batch_size: 32
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: 1e-05
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 5
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: True
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: HassanCS/chemberta-clintox-tunned-3
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
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
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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	all-dev_cosine_ap
1.592	200	-	0.0352	0.4742
3.176	400	-	0.0349	0.4779
3.976	500	0.0343	-	-
4.768	600	-	0.0344	0.4791

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.47.1
PyTorch: 2.5.1+cu124
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.0

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",
}

ContrastiveLoss

bibtex

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}

	smiles1	smiles2	label
type	string	string	int
details	min: 3 tokens mean: 46.57 tokens max: 221 tokens	min: 3 tokens mean: 54.2 tokens max: 221 tokens	0: ~49.40% 1: ~50.60%