You can deploy this model and start earning money today!

tomaarsen/
distilroberta-base-nli-matryoshka-baseline

Name: distilroberta-base-nli-matryoshka-baseline
Availability: InStock

Views

No views yet

SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base on the 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 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- 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, 'architecture': '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/distilroberta-base-nli-matryoshka-baseline")
# Run inference
sentences = [
    'A construction worker peeking out of a manhole while his coworker sits on the sidewalk smiling.',
    'A worker is looking out of a manhole.',
    'The workers are both inside the manhole.',
]
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, 0.7356, 0.5872],
#         [0.7356, 1.0000, 0.6366],
#         [0.5872, 0.6366, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Datasets: sts-dev-768 and sts-test-768
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "truncate_dim": 768 3}

Metric	sts-dev-768	sts-test-768
pearson_cosine	0.7524	0.7147
spearman_cosine	0.7891	0.7266

Semantic Similarity

Datasets: sts-dev-512 and sts-test-512
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "truncate_dim": 512 3}

Metric	sts-dev-512	sts-test-512
pearson_cosine	0.7676	0.722
spearman_cosine	0.796	0.7301

Semantic Similarity

Datasets: sts-dev-256 and sts-test-256
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "truncate_dim": 256 3}

Metric	sts-dev-256	sts-test-256
pearson_cosine	0.7509	0.7147
spearman_cosine	0.7905	0.7282

Semantic Similarity

Datasets: sts-dev-128 and sts-test-128
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "truncate_dim": 128 3}

Metric	sts-dev-128	sts-test-128
pearson_cosine	0.7163	0.6914
spearman_cosine	0.7718	0.7133

Semantic Similarity

Datasets: sts-dev-64 and sts-test-64
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "truncate_dim": 64 3}

Metric	sts-dev-64	sts-test-64
pearson_cosine	0.7364	0.6948
spearman_cosine	0.7766	0.7079

Training Details

Training Dataset

all-nli

Dataset: all-nli at d482672
Size: 25,000 training samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 7 tokens
mean: 10.38 tokens
max: 45 tokens
min: 6 tokens
mean: 12.8 tokens
max: 39 tokens
min: 6 tokens
mean: 13.4 tokens
max: 50 tokens

Samples:

anchor	positive	negative
`A person on a horse jumps over a broken down airplane.`	`A person is outdoors, on a horse.`	`A person is at a diner, ordering an omelette.`
`Children smiling and waving at camera`	`There are children present`	`The kids are frowning`
`A boy is jumping on skateboard in the middle of a red bridge.`	`The boy does a skateboarding trick.`	`The boy skates down the sidewalk.`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Evaluation Dataset

all-nli

Dataset: 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:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 128
num_train_epochs: 1
warmup_steps: 0.1
fp16: True
eval_strategy: steps
per_device_eval_batch_size: 128
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 128
num_train_epochs: 1
max_steps: -1
learning_rate: 5e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
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: steps
per_device_eval_batch_size: 128
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: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev-768_spearman_cosine	sts-dev-512_spearman_cosine	sts-dev-256_spearman_cosine	sts-dev-128_spearman_cosine	sts-dev-64_spearman_cosine	sts-test-768_spearman_cosine	sts-test-512_spearman_cosine	sts-test-256_spearman_cosine	sts-test-128_spearman_cosine	sts-test-64_spearman_cosine
0.1020	20	21.8538	-	-	-	-	-	-	-	-	-	-	-
0.2041	40	11.3759	-	-	-	-	-	-	-	-	-	-	-
0.25	49	-	5.9885	0.7989	0.8082	0.8067	0.7925	0.7973	-	-	-	-	-
0.3061	60	9.0731	-	-	-	-	-	-	-	-	-	-	-
0.4082	80	7.6177	-	-	-	-	-	-	-	-	-	-	-
0.5	98	-	7.2544	0.7918	0.7981	0.7948	0.7791	0.7806	-	-	-	-	-
0.5102	100	6.6966	-	-	-	-	-	-	-	-	-	-	-
0.6122	120	6.1411	-	-	-	-	-	-	-	-	-	-	-
0.7143	140	5.8134	-	-	-	-	-	-	-	-	-	-	-
0.75	147	-	7.5246	0.7892	0.7962	0.7911	0.7720	0.7777	-	-	-	-	-
0.8163	160	5.1003	-	-	-	-	-	-	-	-	-	-	-
0.9184	180	4.8691	-	-	-	-	-	-	-	-	-	-	-
1.0	196	-	7.2495	0.7891	0.7960	0.7905	0.7718	0.7766	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	0.7266	0.7301	0.7282	0.7133	0.7079

Framework Versions

Python: 3.11.6
Sentence Transformers: 5.3.0.dev0
Transformers: 5.2.0.dev0
PyTorch: 2.10.0+cu126
Accelerate: 1.12.0
Datasets: 4.3.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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

bibtex

@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

bibtex

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

	anchor	positive	negative
type	string	string	string
details	min: 7 tokens mean: 10.38 tokens max: 45 tokens	min: 6 tokens mean: 12.8 tokens max: 39 tokens	min: 6 tokens mean: 13.4 tokens max: 50 tokens