Downloads · 30 days
7
8% of all-time downloads
kiarashmo/chembberta-77m-sBERT-finetuned-on-clintox-with-sBERTSoftmaxLoss
chembberta-77m-sBERT-finetuned-on-clintox-with-sBERTSoftmaxLoss 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
7
8% of all-time downloads
All-time downloads
89
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 = [
'CC(C)CNCc1ccc(-c2ccccc2S(=O)(=O)N2CCCC2)cc1',
'C[NH+]1CCN(C(=O)OC2c3nccnc3C(=O)N2c2ccc(Cl)cn2)CC1',
'Cn1c(=O)n(-c2ccc(C(C)(C)C#N)cc2)c2c3cc(-c4cnc5ccccc5c4)ccc3ncc21',
]
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, 0.8166, 0.8574],
# [0.8166, 1.0000, 0.7862],
# [0.8574, 0.7862, 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 | 0.608 |
| cosine_accuracy_threshold | 0.1889 |
| cosine_f1 | 0.6839 |
| cosine_f1_threshold | -0.2283 |
| cosine_precision | 0.5207 |
| cosine_recall | 0.9961 |
| cosine_ap | 0.6766 |
| cosine_mcc | 0.0707 |
| sentence_A | sentence_B | label | |
|---|---|---|---|
| type | string | string | int |
| details | <ul><li>min: 3 tokens</li><li>mean: 50.46 tokens</li><li>max: 189 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 50.44 tokens</li><li>max: 221 tokens</li></ul> | <ul><li>0: ~49.60%</li><li>1: ~50.40%</li></ul> |
| sentence_A | sentence_B | label |
|---|---|---|
| <code>CCSc1ccc2c(c1)N(CCCN1CCNH+CC1)c1ccccc1S2</code> | <code>CCNH+CC(=O)Nc1c(C)cccc1C</code> | <code>1</code> |
| <code>Cc1ncc(COP(=O)([O-])[O-])c(CN(CCNH+Cc2c(COP(=O)([O-])[O-])cnc(C)c2O)CC(=O)[O-])c1O</code> | <code>CCC1=CC2CNH+Cc1c([nH]c3ccccc13)C(C(=O)OC)(c1cc3c(cc1OC)N(C)C1C(O)(C(=O)OC)C(OC(C)=O)C4(CC)C=CC[NH+]5CCC31C54)C2</code> | <code>1</code> |
| <code>CN1C(=O)CCS(=O)(=O)C1c1ccc(Cl)cc1</code> | <code>[NH3+]CC1OC(OC2C([NH3+])CC([NH3+])C(OC3OC(CO)C(O)C([NH3+])C3O)C2O)C(O)C(O)C1O</code> | <code>1</code> |
| sentence_A | sentence_B | label | |
|---|---|---|---|
| type | string | string | int |
| details | <ul><li>min: 18 tokens</li><li>mean: 65.07 tokens</li><li>max: 244 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 66.06 tokens</li><li>max: 244 tokens</li></ul> | <ul><li>0: ~48.30%</li><li>1: ~51.70%</li></ul> |
| sentence_A | sentence_B | label |
|---|---|---|
| <code>C[NH+]1CCC(=C2c3ccccc3CC(=O)c3sccc32)CC1</code> | <code>CC(C)c1nc(N(C)S(C)(=O)=O)nc(-c2ccc(F)cc2)c1C=CC(O)CC(O)CC(=O)[O-]</code> | <code>1</code> |
| <code>CC(C)CC(NC(=O)C(C)NC(=O)CNC(=O)C(NC=O)C(C)C)C(=O)NC(C)C(=O)NC(C(=O)NC(C(=O)NC(C(=O)NC(Cc1c[nH]c2ccccc12)C(=O)NC(CC(C)C)C(=O)NC(Cc1c[nH]c2ccccc12)C(=O)NC(CC(C)C)C(=O)NC(Cc1c[nH]c2ccccc12)C(=O)NC(CC(C)C)C(=O)NC(Cc1c[nH]c2ccccc12)C(=O)NCCO)C(C)C)C(C)C)C(C)C</code> | <code>COC1OC2OC3(C)CCC4C(C)CCC(C1C)C24OO3</code> | <code>1</code> |
| <code>CC12Cc3cn[nH]c3CC1CCC1C2CCC2(C)C1CCC2(C)O</code> | <code>CNH+CCc1c[nH]c2ccc(CC3COC(=O)N3)cc12</code> | <code>1</code> |
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 |
|---|---|---|---|---|
| 0.533 | 500 | 0.6878 | 0.6948 | 0.6314 |
| 1.0661 | 1000 | 0.2852 | 1.5364 | 0.6816 |
| 1.5991 | 1500 | 0.1471 | 2.7704 | 0.6567 |
| 2.1322 | 2000 | 0.1375 | 3.0539 | 0.6778 |
| 2.6652 | 2500 | 0.1235 | 3.5321 | 0.6752 |
| 3.1983 | 3000 | 0.1209 | 3.8966 | 0.6766 |
@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",
}
<!--
## 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.*
-->