eagle0504/distilroberta-base-nli-matryoshka

SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base on the sentence-transformers/all-nli 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: distilbert/distilroberta-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • sentence-transformers/all-nli
• 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: RobertaModel 
  (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("eagle0504/distilroberta-base-nli-matryoshka")
# Run inference
sentences = [
    'Loire Valley',
    'The Valley of Loire.',
    'The people are adults.',
]
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

• Dataset: sts-dev-768
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.817
spearman_cosine	0.8256
pearson_manhattan	0.8085
spearman_manhattan	0.8093
pearson_euclidean	0.809
spearman_euclidean	0.8099
pearson_dot	0.5788
spearman_dot	0.6051
pearson_max	0.817
spearman_max	0.8256

Semantic Similarity

• Dataset: sts-dev-512
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8217
spearman_cosine	0.8277
pearson_manhattan	0.8086
spearman_manhattan	0.809
pearson_euclidean	0.8096
spearman_euclidean	0.8097
pearson_dot	0.636
spearman_dot	0.6594
pearson_max	0.8217
spearman_max	0.8277

Semantic Similarity

• Dataset: sts-dev-256
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8179
spearman_cosine	0.8257
pearson_manhattan	0.8072
spearman_manhattan	0.8081
pearson_euclidean	0.8076
spearman_euclidean	0.8082
pearson_dot	0.6316
spearman_dot	0.6531
pearson_max	0.8179
spearman_max	0.8257

Semantic Similarity

• Dataset: sts-dev-128
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8084
spearman_cosine	0.8195
pearson_manhattan	0.8017
spearman_manhattan	0.8044
pearson_euclidean	0.8005
spearman_euclidean	0.8033
pearson_dot	0.6055
spearman_dot	0.6324
pearson_max	0.8084
spearman_max	0.8195

Semantic Similarity

• Dataset: sts-dev-64
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7969
spearman_cosine	0.8138
pearson_manhattan	0.7907
spearman_manhattan	0.7953
pearson_euclidean	0.7887
spearman_euclidean	0.7935
pearson_dot	0.537
spearman_dot	0.5529
pearson_max	0.7969
spearman_max	0.8138

Semantic Similarity

• Dataset: sts-test-768
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.783
spearman_cosine	0.7774
pearson_manhattan	0.776
spearman_manhattan	0.7572
pearson_euclidean	0.7768
spearman_euclidean	0.7577
pearson_dot	0.5697
spearman_dot	0.5538
pearson_max	0.783
spearman_max	0.7774

Semantic Similarity

• Dataset: sts-test-512
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7908
spearman_cosine	0.7783
pearson_manhattan	0.7765
spearman_manhattan	0.7566
pearson_euclidean	0.7783
spearman_euclidean	0.7587
pearson_dot	0.6258
spearman_dot	0.6182
pearson_max	0.7908
spearman_max	0.7783

Semantic Similarity

• Dataset: sts-test-256
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7908
spearman_cosine	0.7795
pearson_manhattan	0.7755
spearman_manhattan	0.7563
pearson_euclidean	0.7781
spearman_euclidean	0.7588
pearson_dot	0.6154
spearman_dot	0.6087
pearson_max	0.7908
spearman_max	0.7795

Semantic Similarity

• Dataset: sts-test-128
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7835
spearman_cosine	0.7742
pearson_manhattan	0.7699
spearman_manhattan	0.7517
pearson_euclidean	0.7725
spearman_euclidean	0.7541
pearson_dot	0.5993
spearman_dot	0.5948
pearson_max	0.7835
spearman_max	0.7742

Semantic Similarity

• Dataset: sts-test-64
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7698
spearman_cosine	0.7694
pearson_manhattan	0.7567
spearman_manhattan	0.7417
pearson_euclidean	0.7597
spearman_euclidean	0.7445
pearson_dot	0.5374
spearman_dot	0.5338
pearson_max	0.7698
spearman_max	0.7694

Training Details

Training Dataset

sentence-transformers/all-nli

• Dataset: sentence-transformers/all-nli at d482672
• Size: 10,000 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 4 tokens mean: 18.26 tokens max: 88 tokens	min: 4 tokens mean: 11.6 tokens max: 36 tokens	min: 4 tokens mean: 12.09 tokens max: 38 tokens

• Samples:

  anchor	positive	negative
  Side view of a female triathlete during the run.	A woman runs	A man sits
  Confused person standing in the middle of the trolley tracks trying to figure out the signs.	A person is on the tracks.	A man sits in an airplane.
  A woman in a black shirt, jean shorts and white tennis shoes is bowling.	A woman is bowling in casual clothes	A woman bowling wins an outfit of clothes

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Evaluation Dataset

sentence-transformers/all-nli

• Dataset: sentence-transformers/all-nli at d482672
• Size: 6,584 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 6 tokens mean: 18.02 tokens max: 66 tokens	min: 5 tokens mean: 9.81 tokens max: 29 tokens	min: 5 tokens mean: 10.37 tokens max: 29 tokens

• Samples:

  anchor	positive	negative
  Two women are embracing while holding to go packages.	Two woman are holding packages.	The men are fighting outside a deli.
  Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.	Two kids in numbered jerseys wash their hands.	Two kids in jackets walk to school.
  A man selling donuts to a customer during a world exhibition event held in the city of Angeles	A man selling donuts to a customer.	A woman drinks her coffee in a small cafe.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• 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: 128
• per_device_eval_batch_size: 128
• 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: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: 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: 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	sts-dev-128_spearman_cosine	sts-dev-256_spearman_cosine	sts-dev-512_spearman_cosine	sts-dev-64_spearman_cosine	sts-dev-768_spearman_cosine	sts-test-128_spearman_cosine	sts-test-256_spearman_cosine	sts-test-512_spearman_cosine	sts-test-64_spearman_cosine	sts-test-768_spearman_cosine
0.3797	30	15.8875	6.1089	0.8036	0.8123	0.8143	0.8010	0.8076	-	-	-	-	-
0.7595	60	7.4874	5.0189	0.8195	0.8257	0.8277	0.8138	0.8256	-	-	-	-	-
1.0	79	-	-	-	-	-	-	-	0.7742	0.7795	0.7783	0.7694	0.7774

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.0
• Transformers: 4.41.1
• PyTorch: 2.3.0+cu121
• Accelerate: 0.30.1
• Datasets: 2.19.1
• 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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning}, 
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}