You can deploy this model and start earning money today!

Views

No views yet

SentenceTransformer based on distilbert/distilroberta-base

Name: distilroberta-base-nli-2d-matryoshka
Availability: InStock

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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/distilroberta-base-nli-2d-matryoshka")
# Run inference
sentences = [
    'A plane in the sky.',
    'Two airplanes in the sky.',
    'Nelson Mandela undergoes surgery',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8395
spearman_cosine	0.8425
pearson_manhattan	0.8433
spearman_manhattan	0.8436
pearson_euclidean	0.8441
spearman_euclidean	0.8449
pearson_dot	0.7638
spearman_dot	0.757
pearson_max	0.8441
spearman_max	0.8449

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8187
spearman_cosine	0.8171
pearson_manhattan	0.8117
spearman_manhattan	0.8049
pearson_euclidean	0.8127
spearman_euclidean	0.8058
pearson_dot	0.7396
spearman_dot	0.7256
pearson_max	0.8187
spearman_max	0.8171

Training Details

Training Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli at 65dd388
Size: 557,850 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: Matryoshka2dLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "n_layers_per_step": 1, 4 "last_layer_weight": 1.0, 5 "prior_layers_weight": 1.0, 6 "kl_div_weight": 1.0, 7 "kl_temperature": 0.3, 8 "matryoshka_dims": [ 9 768, 10 512, 11 256, 12 128, 13 64 14 ], 15 "matryoshka_weights": [ 16 1, 17 1, 18 1, 19 1, 20 1 21 ], 22 "n_dims_per_step": 1 23}

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: 15.0 tokens
max: 44 tokens
min: 6 tokens
mean: 14.99 tokens
max: 61 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: Matryoshka2dLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "n_layers_per_step": 1, 4 "last_layer_weight": 1.0, 5 "prior_layers_weight": 1.0, 6 "kl_div_weight": 1.0, 7 "kl_temperature": 0.3, 8 "matryoshka_dims": [ 9 768, 10 512, 11 256, 12 128, 13 64 14 ], 15 "matryoshka_weights": [ 16 1, 17 1, 18 1, 19 1, 20 1 21 ], 22 "n_dims_per_step": 1 23}

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: False
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
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: None
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_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	sts-dev_spearman_cosine	sts-test_spearman_cosine
0.0229	100	6.2779	3.9959	0.8008	-
0.0459	200	4.3212	3.5818	0.7956	-
0.0688	300	3.7135	3.4422	0.7940	-
0.0918	400	3.5567	3.5458	0.7951	-
0.1147	500	3.1297	3.1253	0.8050	-
0.1376	600	2.7001	3.4366	0.7996	-
0.1606	700	2.8664	3.6609	0.8033	-
0.1835	800	2.6656	3.3736	0.7975	-
0.2065	900	2.633	3.3735	0.8076	-
0.2294	1000	2.4335	3.6499	0.7996	-
0.2524	1100	2.4165	3.6301	0.8015	-
0.2753	1200	2.2942	3.1541	0.7994	-
0.2982	1300	2.2402	3.4284	0.7977	-
0.3212	1400	2.2148	3.3775	0.7988	-
0.3441	1500	2.2285	3.6097	0.8016	-
0.3671	1600	2.0591	3.3839	0.7926	-
0.3900	1700	2.0253	3.1113	0.7981	-
0.4129	1800	2.0244	3.8289	0.7954	-
0.4359	1900	1.8582	3.3515	0.8000	-
0.4588	2000	1.977	3.3054	0.7917	-
0.4818	2100	1.9028	3.2166	0.7927	-
0.5047	2200	1.8316	3.6504	0.7955	-
0.5276	2300	1.8404	3.2822	0.7843	-
0.5506	2400	1.8455	3.2583	0.7941	-
0.5735	2500	1.9488	3.3970	0.7971	-
0.5965	2600	1.9403	2.8948	0.7959	-
0.6194	2700	1.8884	3.2227	0.8008	-
0.6423	2800	1.8655	3.1948	0.7920	-
0.6653	2900	1.8567	3.4374	0.7913	-
0.6882	3000	1.8423	3.1118	0.7949	-
0.7112	3100	1.7475	3.1359	0.8062	-
0.7341	3200	1.8166	2.9927	0.7984	-
0.7571	3300	1.5626	3.5143	0.8405	-
0.7800	3400	1.2038	3.3909	0.8411	-
0.8029	3500	1.1579	3.2458	0.8413	-
0.8259	3600	1.0978	3.1592	0.8404	-
0.8488	3700	1.0283	2.9557	0.8408	-
0.8718	3800	0.9993	3.4073	0.8430	-
0.8947	3900	0.9727	3.0570	0.8434	-
0.9176	4000	0.9692	2.9357	0.8439	-
0.9406	4100	0.9412	2.9494	0.8428	-
0.9635	4200	1.0063	3.4047	0.8422	-
0.9865	4300	0.9678	3.4299	0.8425	-
1.0	4359	-	-	-	0.8171

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.178 kWh
Carbon Emitted: 0.069 kg of CO2
Hours Used: 0.626 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 3.0.0.dev0
Transformers: 4.41.0.dev0
PyTorch: 2.3.0+cu121
Accelerate: 0.26.1
Datasets: 2.18.0
Tokenizers: 0.19.1

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",
}

Matryoshka2dLoss

bibtex

@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}
}

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{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}
}

	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