Hugging Face's logo

bobox
/
DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2

Sentence Similarity
sentence-transformers
PyTorch
English
deberta-v2
feature-extraction
Generated from Trainer
dataset_size:67190
loss:AdaptiveLayerLoss
loss:MultipleNegativesRankingLoss
Eval Results
Inference Endpoints
Model card Files Community
DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2 / README.md
bobox's picture
bobox
n_layers_per_step = 1, last_layer_weight = 1 * model_layers,, prior_layers_weight= 0.05, kl_div_weight = 2, kl_temperature= 0.9,
aa1484c verified
preview code
|
raw
history blame contribute delete
23.6 kB
metadata
language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:67190
  - loss:AdaptiveLayerLoss
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/deberta-v3-small
datasets:
  - stanfordnlp/snli
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
widget:
  - source_sentence: A man is walking past a large sign that says E.S.E. Electronics.
    sentences:
      - a child opens a present on his birthday
      - The man works at E.S.E Electronics.
      - The soccer team in blue plays soccer.
  - source_sentence: This child is on the library steps.
    sentences:
      - A mother dog checking up on her baby puppy.
      - A guy bites into a freshly opened marshmallow chick
      - The child is on the steps inside the library.
  - source_sentence: Two men are standing in a boat.
    sentences:
      - People are watching the flowers blossom
      - The couple is married.
      - A few men are fishing on a boat.
  - source_sentence: >-
      Four men playing drums in very orange lighting while one of them is also
      drinking something out of a bottle.
    sentences:
      - four men play drums
      - The man puts something on the other mans head.
      - The dogs are in the backyard.
  - source_sentence: >-
      First Lady Laura Bush at podium, in front of seated audience, at the White
      House Conference on Global Literacy.
    sentences:
      - Some people are exercising outside.
      - The former First Lady is at the podium for a conference.
      - This person is going to the waterfall
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on microsoft/deberta-v3-small
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.6651071536371869
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.687929630279541
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.7077349458301839
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.6304811239242554
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.6222862206468763
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8203855140186916
            name: Cosine Recall
          - type: cosine_ap
            value: 0.7058220689813709
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.6313009357078176
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 135.98495483398438
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.6997334569475027
            name: Dot F1
          - type: dot_f1_threshold
            value: 115.54609680175781
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.5800192122958694
            name: Dot Precision
          - type: dot_recall
            value: 0.8817172897196262
            name: Dot Recall
          - type: dot_ap
            value: 0.6554755795160082
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.6708421370359191
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 219.32388305664062
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.7119951778179626
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 262.314697265625
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.6062410182714022
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.8624415887850467
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.7135236162968746
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.6652580742529429
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 11.506816864013672
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.7080090384132564
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 12.478536605834961
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.6208718626155878
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.8235981308411215
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.7090362803652147
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.6708421370359191
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 219.32388305664062
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.7119951778179626
            name: Max F1
          - type: max_f1_threshold
            value: 262.314697265625
            name: Max F1 Threshold
          - type: max_precision
            value: 0.6222862206468763
            name: Max Precision
          - type: max_recall
            value: 0.8817172897196262
            name: Max Recall
          - type: max_ap
            value: 0.7135236162968746
            name: Max Ap

SentenceTransformer based on microsoft/deberta-v3-small

This is a sentence-transformers model finetuned from microsoft/deberta-v3-small on the stanfordnlp/snli 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: microsoft/deberta-v3-small
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Training Dataset:
  • Language: en

Model Sources

Full Model Architecture 

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
  (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("bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2")
# Run inference
sentences = [
    'First Lady Laura Bush at podium, in front of seated audience, at the White House Conference on Global Literacy.',
    'The former First Lady is at the podium for a conference.',
    'This person is going to the waterfall',
]
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]

Evaluation

Metrics

Binary Classification

Metric Value
cosine_accuracy 0.6651
cosine_accuracy_threshold 0.6879
cosine_f1 0.7077
cosine_f1_threshold 0.6305
cosine_precision 0.6223
cosine_recall 0.8204
cosine_ap 0.7058
dot_accuracy 0.6313
dot_accuracy_threshold 135.985
dot_f1 0.6997
dot_f1_threshold 115.5461
dot_precision 0.58
dot_recall 0.8817
dot_ap 0.6555
manhattan_accuracy 0.6708
manhattan_accuracy_threshold 219.3239
manhattan_f1 0.712
manhattan_f1_threshold 262.3147
manhattan_precision 0.6062
manhattan_recall 0.8624
manhattan_ap 0.7135
euclidean_accuracy 0.6653
euclidean_accuracy_threshold 11.5068
euclidean_f1 0.708
euclidean_f1_threshold 12.4785
euclidean_precision 0.6209
euclidean_recall 0.8236
euclidean_ap 0.709
max_accuracy 0.6708
max_accuracy_threshold 219.3239
max_f1 0.712
max_f1_threshold 262.3147
max_precision 0.6223
max_recall 0.8817
max_ap 0.7135

Training Details

Training Dataset

stanfordnlp/snli

  • Dataset: stanfordnlp/snli at cdb5c3d
  • Size: 67,190 training samples
  • Columns: sentence1, sentence2, and label
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 label
    type string string int
    details
    • min: 4 tokens
    • mean: 21.19 tokens
    • max: 133 tokens
    • min: 4 tokens
    • mean: 11.77 tokens
    • max: 49 tokens
    • 0: 100.00%
  • Samples:
    sentence1 sentence2 label
    Without a placebo group, we still won't know if any of the treatments are better than nothing and therefore worth giving. It is necessary to use a controlled method to ensure the treatments are worthwhile. 0
    It was conducted in silence. It was done silently. 0
    oh Lewisville any decent food in your cafeteria up there Is there any decent food in your cafeteria up there in Lewisville? 0
  • Loss: AdaptiveLayerLoss with these parameters:
    {
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 0.05,
    "kl_div_weight": 2,
    "kl_temperature": 0.9
}

Evaluation Dataset

stanfordnlp/snli

  • Dataset: stanfordnlp/snli at cdb5c3d
  • Size: 6,626 evaluation samples
  • Columns: premise, hypothesis, and label
  • Approximate statistics based on the first 1000 samples:
    premise hypothesis label
    type string string int
    details
    • min: 6 tokens
    • mean: 17.28 tokens
    • max: 59 tokens
    • min: 4 tokens
    • mean: 10.53 tokens
    • max: 32 tokens
    • 0: ~48.70%
    • 1: ~51.30%
  • Samples:
    premise hypothesis label
    This church choir sings to the masses as they sing joyous songs from the book at a church. The church has cracks in the ceiling. 0
    This church choir sings to the masses as they sing joyous songs from the book at a church. The church is filled with song. 1
    A woman with a green headscarf, blue shirt and a very big grin. The woman is young. 0
  • Loss: AdaptiveLayerLoss with these parameters:
    {
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 0.05,
    "kl_div_weight": 2,
    "kl_temperature": 0.9
}

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 45
  • per_device_eval_batch_size: 22
  • learning_rate: 3e-06
  • weight_decay: 1e-09
  • num_train_epochs: 2
  • lr_scheduler_type: cosine
  • warmup_ratio: 0.5
  • save_safetensors: False
  • fp16: True
  • push_to_hub: True
  • hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
  • hub_strategy: checkpoint
  • 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: 45
  • per_device_eval_batch_size: 22
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_steps: None
  • learning_rate: 3e-06
  • weight_decay: 1e-09
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • max_grad_norm: 1.0
  • num_train_epochs: 2
  • max_steps: -1
  • lr_scheduler_type: cosine
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.5
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: False
  • 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: 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: True
  • resume_from_checkpoint: None
  • hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayer-Norm-ep2-checkpoints
  • hub_strategy: checkpoint
  • 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
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss loss max_ap
0.1004 150 4.5827 - -
0.2001 299 - 3.5735 0.6133
0.2008 300 3.5451 - -
0.3012 450 2.9066 - -
0.4003 598 - 2.8785 0.6561
0.4016 600 2.5141 - -
0.5020 750 2.0248 - -
0.6004 897 - 2.1300 0.6917
0.6024 900 1.6782 - -
0.7028 1050 1.4187 - -
0.8005 1196 - 1.7111 0.7051
0.8032 1200 1.2446 - -
0.9036 1350 1.1078 - -
1.0007 1495 - 1.4859 0.7108
1.0040 1500 0.9827 - -
1.1044 1650 0.9335 - -
1.2008 1794 - 1.3516 0.7121
1.2048 1800 0.8595 - -
1.3052 1950 0.8362 - -
1.4009 2093 - 1.2659 0.7147
1.4056 2100 0.8167 - -
1.5060 2250 0.7695 - -
1.6011 2392 - 1.2218 0.7135
1.6064 2400 0.7544 - -
1.7068 2550 0.7625 - -
1.8012 2691 - 1.2073 0.7135
1.8072 2700 0.7366 - -
1.9076 2850 0.7348 - -

Framework Versions

  • Python: 3.10.13
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.1.2
  • Accelerate: 0.30.1
  • Datasets: 2.19.2
  • 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",
}

AdaptiveLayerLoss 

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings}, 
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

MultipleNegativesRankingLoss 

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}