TTM_1239_12_15_0.0001_Adafactor

SentenceTransformer based on google-bert/bert-base-cased

This is a sentence-transformers model finetuned from 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 <!-- at revision cd5ef92a9fb2f889e972770a36d4ed042daf221e -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • csv

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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, '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:

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("Jimmy-Ooi/TTM_1239_12_15_0.0001_Adafactor")
# Run inference
sentences = [
    'C=C(C)[C@@H]1CC[C@]2(C(=O)O)CC[C@]3(C)[C@H](CC[C@@H]4[C@@]5(C)CC[C@@H](O)[C@@](C)(C=O)[C@@H]5CC[C@]43C)[C@@H]12',
    'CC(C)C[C@H](NC(=O)OCc1ccccc1)C(=O)OCc1cc(=O)c(O)c[nH]1',
    'COc1cc(/C=C/C(=O)CC(=O)/C=C/c2ccc(O)c(OC)c2)ccc1O',
]
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,  0.9881, -0.3091],
#         [ 0.9881,  1.0000, -0.4174],
#         [-0.3091, -0.4174,  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.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

csv

• Dataset: csv
• Size: 286,816 training samples
• Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	<ul><li>min: 8 tokens</li><li>mean: 37.82 tokens</li><li>max: 213 tokens</li></ul>	<ul><li>min: 8 tokens</li><li>mean: 39.29 tokens</li><li>max: 213 tokens</li></ul>	<ul><li>0: ~50.00%</li><li>2: ~50.00%</li></ul>

• Samples:

  premise	hypothesis	label
  <code>COc1cc([C@H]2Oc3ccc([C@H]4Oc5cc(O)cc(O)c5C(=O)[C@@H]4O)cc3O[C@@H]2CO)ccc1O</code>	<code>COc1cccc(OC(=O)COC(=O)/C=C/c2ccccc2)c1</code>	<code>0</code>
  <code>Oc1ccc(-c2csc(NC3CCCCC3)n2)c(O)c1</code>	<code>C=C(C)[C@@H]1CC[C@]2(C(=O)O)CC[C@]3(C)C@H[C@@H]12</code>	<code>0</code>
  <code>COc1cccc(OC(=O)COC(=O)/C=C/c2ccc(O)cc2)c1</code>	<code>COc1ccc(C(C)=O)c(OC(=O)/C=C/c2ccc(F)cc2)c1</code>	<code>2</code>

• Loss: <code>SoftmaxLoss</code>

Evaluation Dataset

csv

• Dataset: csv
• Size: 50,615 evaluation samples
• Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	<ul><li>min: 8 tokens</li><li>mean: 38.57 tokens</li><li>max: 213 tokens</li></ul>	<ul><li>min: 8 tokens</li><li>mean: 39.19 tokens</li><li>max: 213 tokens</li></ul>	<ul><li>0: ~52.00%</li><li>2: ~48.00%</li></ul>

• Samples:

  premise	hypothesis	label
  <code>Nc1ccccc1C(=O)N1CCN(Cc2ccc(F)cc2)CC1</code>	<code>COc1cc(OC)c(C2CCN(C)C2CO)c(O)c1-c1cc(-c2ccc(N+[O-])cc2Cl)[nH]n1</code>	<code>0</code>
  <code>Cc1c(C)c2c(c(C)c1O)CCC(C)(C(=O)OCc1cc(=O)c(O)co1)O2</code>	<code>CCCNc1nc(-c2ccc(O)cc2O)cs1</code>	<code>0</code>
  <code>Oc1ccc(/N=C/c2ccc(O)c(O)c2)cc1</code>	<code>O=C(c1ccc(O)cc1)N1CCN(Cc2ccc(F)cc2)CC1</code>	<code>0</code>

• Loss: <code>SoftmaxLoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• num_train_epochs: 15
• warmup_steps: 100
• optim: adafactor
• weight_decay: 0.0001
• fp16: True
• per_device_eval_batch_size: 64

All Hyperparameters

<details><summary>Click to expand</summary>

• per_device_train_batch_size: 64
• num_train_epochs: 15
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 100
• optim: adafactor
• optim_args: None
• weight_decay: 0.0001
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: trackio
• eval_strategy: no
• per_device_eval_batch_size: 64
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• 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
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

<details><summary>Click to expand</summary> </details>

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.3.0
• Transformers: 5.5.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@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.* -->