bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerBaseline

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:
  • stanfordnlp/snli
• Language: en

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: 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-SentenceTransformer-AdaptiveLayerBaseline")
# Run inference
sentences = [
    'people are standing near water with a boat heading their direction',
    'People are standing near water with a large blue boat heading their direction.',
    'The dogs are near the toy.',
]
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

Semantic Similarity

• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.766
spearman_cosine	0.7681
pearson_manhattan	0.7918
spearman_manhattan	0.7947
pearson_euclidean	0.7861
spearman_euclidean	0.7896
pearson_dot	0.6448
spearman_dot	0.6428
pearson_max	0.7918
spearman_max	0.7947

Binary Classification

• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.6731
cosine_accuracy_threshold	0.5815
cosine_f1	0.717
cosine_f1_threshold	0.4671
cosine_precision	0.5977
cosine_recall	0.8959
cosine_ap	0.7193
dot_accuracy	0.6445
dot_accuracy_threshold	71.9551
dot_f1	0.7094
dot_f1_threshold	53.7729
dot_precision	0.5779
dot_recall	0.9184
dot_ap	0.6828
manhattan_accuracy	0.6665
manhattan_accuracy_threshold	213.6252
manhattan_f1	0.7047
manhattan_f1_threshold	245.2058
manhattan_precision	0.5908
manhattan_recall	0.8729
manhattan_ap	0.7132
euclidean_accuracy	0.6621
euclidean_accuracy_threshold	10.3589
euclidean_f1	0.7024
euclidean_f1_threshold	12.0109
euclidean_precision	0.5865
euclidean_recall	0.8754
euclidean_ap	0.7102
max_accuracy	0.6731
max_accuracy_threshold	213.6252
max_f1	0.717
max_f1_threshold	245.2058
max_precision	0.5977
max_recall	0.9184
max_ap	0.7193

Training Details

Training Dataset

stanfordnlp/snli

• Dataset: stanfordnlp/snli at cdb5c3d
• Size: 314,315 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 5 tokens mean: 16.62 tokens max: 62 tokens	min: 4 tokens mean: 9.46 tokens max: 29 tokens	0: 100.00%

• Samples:

  sentence1	sentence2	label
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	0
  Children smiling and waving at camera	There are children present	0
  A boy is jumping on skateboard in the middle of a red bridge.	The boy does a skateboarding trick.	0

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "n_layers_per_step": 1,
      "last_layer_weight": 1,
      "prior_layers_weight": 1,
      "kl_div_weight": 1.2,
      "kl_temperature": 1.2
  }
  

Evaluation Dataset

sentence-transformers/stsb

• Dataset: sentence-transformers/stsb at ab7a5ac
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 5 tokens mean: 14.77 tokens max: 45 tokens	min: 6 tokens mean: 14.74 tokens max: 49 tokens	min: 0.0 mean: 0.47 max: 1.0

• Samples:

  sentence1	sentence2	score
  A man with a hard hat is dancing.	A man wearing a hard hat is dancing.	1.0
  A young child is riding a horse.	A child is riding a horse.	0.95
  A man is feeding a mouse to a snake.	The man is feeding a mouse to the snake.	1.0

• Loss: AdaptiveLayerLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "n_layers_per_step": 1,
      "last_layer_weight": 1,
      "prior_layers_weight": 1,
      "kl_div_weight": 1.2,
      "kl_temperature": 1.2
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• learning_rate: 5e-06
• weight_decay: 1e-07
• num_train_epochs: 2
• warmup_ratio: 0.5
• save_safetensors: False
• fp16: True
• push_to_hub: True
• hub_model_id: bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerBaselinen
• 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: 32
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 5e-06
• weight_decay: 1e-07
• 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: linear
• 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-SentenceTransformer-AdaptiveLayerBaselinen
• 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	spearman_cosine
None	0	-	4.1425	-	0.4276
0.1001	983	4.7699	3.8387	0.6364	-
0.2001	1966	3.5997	2.7649	0.6722	-
0.3002	2949	2.811	2.3520	0.6838	-
0.4003	3932	2.414	2.0700	0.6883	-
0.5004	4915	2.186	1.8993	0.6913	-
0.6004	5898	1.8523	1.5632	0.7045	-
0.7005	6881	0.6415	1.4902	0.7082	-
0.8006	7864	0.5016	1.4636	0.7108	-
0.9006	8847	0.4194	1.3875	0.7121	-
1.0007	9830	0.3737	1.3077	0.7117	-
1.1008	10813	1.8087	1.0903	0.7172	-
1.2009	11796	1.6631	1.0388	0.7180	-
1.3009	12779	1.6161	1.0177	0.7169	-
1.4010	13762	1.5378	1.0136	0.7148	-
1.5011	14745	1.5215	1.0053	0.7159	-
1.6011	15728	1.2887	0.9600	0.7166	-
1.7012	16711	0.3058	0.9949	0.7180	-
1.8013	17694	0.2897	0.9792	0.7186	-
1.9014	18677	0.275	0.9598	0.7192	-
2.0	19646	-	0.9796	0.7193	-
None	0	-	2.4594	0.7193	0.7681

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}
}