README.md

metadata

base_model: google-bert/bert-base-uncased
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:100000
  - loss:DenoisingAutoEncoderLoss
widget:
  - source_sentence: 1109/icnsurv
    sentences:
      - 1109/icnsurv
      - >-
        A cost function is needed to assign a performance metric value to a
        particular test run
      - >-
        Aircraft OperationsFuture aircraft will sense, control, communicate, and
        navigate with increasing levels of autonomy, enabling new concepts in
        air traffic management
  - source_sentence: Table 1 of and to well as the median taxi from STBO KDFW
    sentences:
      - >-
        Table 1 Metrics of accuracy, median and MAD of residuals as compared to
        STBO predictions, as well as the median taxi time from STBO for KDFW and
        KCLT airports
      - ', IEEE, 2005, pp'
      - 'RESULTS: EFFICIENCY ANALYSIS'
  - source_sentence: gate time to known
    sentences:
      - >-
        3FIVE INPUT VARIABLESParameterDescriptionHead windHead WindGust windGust
        WindCeiling_ftForecast CeilingVis_ftForecast VisibilityAct_Land_Wgt
        Actual Landing Weightfive parameters listed in
      - Instead, gate departure time was assumed to be known
      - >-
        The proof is very similar to that presented for the NP-completeness of
        ASP, and is based on reduction from PLANAR-P3( 6), hence we simply
        provide the main idea of the proof
  - source_sentence: ', Hough" Pattern Recognition, Vol'
    sentences:
      - 9 Station Keeping scores
      - "\t\tAGARD CD-410"
      - >-
        , "Generalizing the Hough Transform to Detect Arbitrary Shapes," Pattern
        Recognition, Vol
  - source_sentence: Airlines often ferry from locations fuel prices
    sentences:
      - >-
        Scheduler Inputs and Order of ConsiderationThe surface model provides
        EOBT, UOBT, UTOT and other detailed flight-specific modeled input
      - "\t\t\tKeithWichman"
      - Airlines often ferry fuel from locations where fuel prices are cheapest

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

This is a sentence-transformers model finetuned from google-bert/bert-base-uncased. 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-uncased
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• 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: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("kathleenge/tsdae-bert-base-uncased")
# Run inference
sentences = [
    'Airlines often ferry from locations fuel prices',
    'Airlines often ferry fuel from locations where fuel prices are cheapest',
    '\t\t\tKeithWichman',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

• Size: 100,000 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 3 tokens mean: 10.95 tokens max: 106 tokens	min: 4 tokens mean: 23.39 tokens max: 239 tokens

• Samples:

  sentence_0	sentence_1
  selected and reviewed for value current on metroplex	The literature was selected and reviewed for its value to the current research on metroplex operations
  and	, and Dulchinos, V
  ,	, Atkins, S

• Loss: DenoisingAutoEncoderLoss

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 1
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: False
• 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: False
• 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: None
• hub_strategy: every_save
• hub_private_repo: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.04	500	7.3777
0.08	1000	6.9771
0.12	1500	6.8481
0.16	2000	6.7737
0.2	2500	6.6935
0.24	3000	6.6264
0.28	3500	6.5918
0.32	4000	6.5504
0.36	4500	6.4805
0.4	5000	6.4539
0.44	5500	6.4242
0.48	6000	6.4017
0.52	6500	6.3808
0.56	7000	6.3595
0.6	7500	6.3174
0.64	8000	6.2911
0.68	8500	6.2917
0.72	9000	6.2555
0.76	9500	6.2314
0.8	10000	6.2223
0.84	10500	6.1852
0.88	11000	6.2067
0.92	11500	6.1562
0.96	12000	6.1563
1.0	12500	6.092

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.32.1
• Datasets: 2.20.0
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@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",
}

DenoisingAutoEncoderLoss

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna", 
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}