Downloads · 30 days
10
11% of all-time downloads
kiarashmo/chembberta-77m-sBERT-finetuned-on-clintox-with-sBERTTripletLoss
chembberta-77m-sBERT-finetuned-on-clintox-with-sBERTTripletLoss is a sentence similarity model from kiarashmo. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model finetuned from kiarashmo/chembberta-77m-mlm-safetensors. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, se…
Downloads · 30 days
10
11% of all-time downloads
All-time downloads
87
Public
Parameters
3.4M
40 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors27.4 MB · 51%
From the Hugging Face model README
This is a sentence-transformers model finetuned from kiarashmo/chembberta-77m-mlm-safetensors. 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.
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': '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})
)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'COc1cc2c(Nc3ccc(Br)cc3F)ncnc2cc1OCC1CC[NH+](C)CC1',
'C#CC1(O)CCC2C3CCC4=C(CCC(=O)C4)C3CCC21C',
'CC(C)CC(NC(=O)C(CCc1ccccc1)NC(=O)CN1CCOCC1)C(=O)NC(Cc1ccccc1)C(=O)NC(CC(C)C)C(=O)C1(C)CO1',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6632, 0.7327],
# [0.6632, 1.0000, 0.4398],
# [0.7327, 0.4398, 1.0000]])
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
val-sim| Metric | Value |
|---|---|
| cosine_accuracy | 0.569 |
| cosine_accuracy_threshold | 0.7855 |
| cosine_f1 | 0.6807 |
| cosine_f1_threshold | -0.4397 |
| cosine_precision | 0.5165 |
| cosine_recall | 0.9981 |
| cosine_ap | 0.6169 |
| cosine_mcc | -0.0306 |
| anchor | positive | negative | |
|---|---|---|---|
| type | string | string | string |
| details | <ul><li>min: 3 tokens</li><li>mean: 51.66 tokens</li><li>max: 221 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 49.04 tokens</li><li>max: 170 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 49.23 tokens</li><li>max: 189 tokens</li></ul> |
| anchor | positive | negative |
|---|---|---|
| <code>CCSc1ccc2c(c1)N(CCCN1CCNH+CC1)c1ccccc1S2</code> | <code>CC(C)([NH3+])Cc1ccc(Cl)cc1</code> | <code>Nc1nc(=O)c2c(CCc3ccc(C(=O)NC(CCC(=O)O)C(=O)O)cc3)c[nH]c2[nH]1</code> |
| <code>CN1C(=O)CCS(=O)(=O)C1c1ccc(Cl)cc1</code> | <code>CCC(=O)OC1(C(=O)SCF)C(C)CC2C3CC(F)C4=CC(=O)C=CC4(C)C3(F)C(O)CC21C</code> | <code>COc1cc(C2c3cc4c(cc3C(OC3OC5COC(C)OC5C(O)C3O)C3COC(=O)C23)OCO4)cc(OC)c1O</code> |
| <code>CCN(CC)CCNC(=O)c1c(C)[nH]c(C=C2C(=O)Nc3ccc(F)cc32)c1C.O=C(O)CC(O)C(=O)O</code> | <code>Nc1nc(=O)c2c(CCc3ccc(C(=O)NC(CCC(=O)O)C(=O)O)cc3)c[nH]c2[nH]1</code> | <code>O=S(=O)([O-])CCS</code> |
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
| anchor | positive | negative | |
|---|---|---|---|
| type | string | string | string |
| details | <ul><li>min: 18 tokens</li><li>mean: 64.71 tokens</li><li>max: 244 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 65.86 tokens</li><li>max: 244 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 65.65 tokens</li><li>max: 244 tokens</li></ul> |
| anchor | positive | negative |
|---|---|---|
| <code>C[NH+]1CCC(=C2c3ccccc3CC(=O)c3sccc32)CC1</code> | <code>CC(C)CC(NC(=O)CNC(=O)C(Cc1ccc(O)cc1)NC(=O)C(CO)NC(=O)C(Cc1c[nH]c2ccccc12)NC(=O)C(Cc1c[nH]cn1)NC(=O)C1CCC(=O)N1)C(=O)NC(CCCNC(N)=[NH2+])C(=O)N1CCCC1C(=O)NCC(N)=O</code> | <code>C=C1CC2CCC34CC5OC6C(OC7CCC(CC(=O)CC8C(CC9OC(CCC1O2)CC(C)C9=C)OC(CC(O)CN)C8OC)OC7C6O3)C5O4</code> |
| <code>CC12Cc3cn[nH]c3CC1CCC1C2CCC2(C)C1CCC2(C)O</code> | <code>C[NH2+]CCCC12CCC(c3ccccc31)c1ccccc12</code> | <code>CC(C)CNCc1ccc(-c2ccccc2S(=O)(=O)N2CCCC2)cc1</code> |
| <code>C[NH+]1CCN2c3ncccc3Cc3ccccc3C2C1</code> | <code>CC12CC(=C[O-])C(=O)CC1CCC1C2CCC2(C)C1CCC2(C)O</code> | <code>C=C1CC2CCC34CC5OC6C(OC7CCC(CC(=O)CC8C(CC9OC(CCC1O2)CC(C)C9=C)OC(CC(O)CN)C8OC)OC7C6O3)C5O4</code> |
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
eval_strategy: stepsper_device_train_batch_size: 32per_device_eval_batch_size: 32num_train_epochs: 100warmup_steps: 100load_best_model_at_end: Trueoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 32per_device_eval_batch_size: 32per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 100max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.0warmup_steps: 100log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Trueignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss | Validation Loss | val-sim_cosine_ap |
|---|---|---|---|---|
| 0.5330 | 500 | 5.0139 | 5.1365 | 0.6009 |
| 1.0661 | 1000 | 5.0062 | 5.1137 | 0.5917 |
| 1.5991 | 1500 | 4.9729 | 5.1148 | 0.6041 |
| 2.1322 | 2000 | 4.9677 | 5.0981 | 0.5961 |
| 2.6652 | 2500 | 4.9218 | 5.1005 | 0.6053 |
| 3.1983 | 3000 | 4.8757 | 5.1119 | 0.6021 |
| 3.7313 | 3500 | 4.8799 | 5.1401 | 0.5959 |
| 4.2644 | 4000 | 4.8248 | 5.1529 | 0.6023 |
| 4.7974 | 4500 | 4.8285 | 5.2060 | 0.6169 |
@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",
}
@misc{hermans2017defense,
title={In Defense of the Triplet Loss for Person Re-Identification},
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
year={2017},
eprint={1703.07737},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->