SentenceTransformer based on FacebookAI/xlm-roberta-large

This is a sentence-transformers model finetuned from FacebookAI/xlm-roberta-large on the sentence-transformers/stsb dataset. It maps sentences & paragraphs to a 1024-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: FacebookAI/xlm-roberta-large
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- sentence-transformers/stsb
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: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("dipteshkanojia/xlm-roberta-large-sts-matryoshka")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man plays the guitar.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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	nan
spearman_cosine	nan
pearson_manhattan	-0.0381
spearman_manhattan	-0.0309
pearson_euclidean	-0.0742
spearman_euclidean	-0.0161
pearson_dot	-0.0532
spearman_dot	-0.0386
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-dev-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0408
spearman_manhattan	-0.0281
pearson_euclidean	-0.0761
spearman_euclidean	-0.0146
pearson_dot	-0.0611
spearman_dot	-0.0482
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-dev-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0442
spearman_manhattan	-0.0325
pearson_euclidean	-0.0529
spearman_euclidean	-0.0338
pearson_dot	0.0887
spearman_dot	0.0689
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-dev-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0532
spearman_manhattan	-0.0265
pearson_euclidean	-0.0606
spearman_euclidean	-0.0271
pearson_dot	0.072
spearman_dot	0.0555
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-dev-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0469
spearman_manhattan	-0.0275
pearson_euclidean	-0.0493
spearman_euclidean	-0.0229
pearson_dot	0.0585
spearman_dot	0.0449
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	0.0005
spearman_manhattan	0.0079
pearson_euclidean	-0.0085
spearman_euclidean	0.0002
pearson_dot	0.0153
spearman_dot	-0.0025
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.001
spearman_manhattan	0.0092
pearson_euclidean	-0.011
spearman_euclidean	0.0006
pearson_dot	0.0309
spearman_dot	0.0214
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0083
spearman_manhattan	0.0081
pearson_euclidean	-0.0128
spearman_euclidean	0.0062
pearson_dot	-0.1041
spearman_dot	-0.1044
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0073
spearman_manhattan	0.0125
pearson_euclidean	-0.0138
spearman_euclidean	0.0084
pearson_dot	-0.0779
spearman_dot	-0.0828
pearson_max	nan
spearman_max	nan

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan
pearson_manhattan	-0.0127
spearman_manhattan	0.0035
pearson_euclidean	-0.0137
spearman_euclidean	0.0028
pearson_dot	-0.049
spearman_dot	-0.0552
pearson_max	nan
spearman_max	nan

Training Details

Training Dataset

sentence-transformers/stsb

Dataset: sentence-transformers/stsb at ab7a5ac
Size: 5,749 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 11.08 tokens
max: 30 tokens

min: 7 tokens
mean: 11.05 tokens
max: 30 tokens

min: 0.0
mean: 0.54
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 11.08 tokens max: 30 tokens	min: 7 tokens mean: 11.05 tokens max: 30 tokens	min: 0.0 mean: 0.54 max: 1.0

Samples:

sentence1	sentence2	score
`A plane is taking off.`	`An air plane is taking off.`	`1.0`
`A man is playing a large flute.`	`A man is playing a flute.`	`0.76`
`A man is spreading shreded cheese on a pizza.`	`A man is spreading shredded cheese on an uncooked pizza.`	`0.76`

Loss: MatryoshkaLoss with these parameters:

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

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: 16.55 tokens
max: 47 tokens

min: 7 tokens
mean: 16.5 tokens
max: 47 tokens

min: 0.0
mean: 0.47
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 16.55 tokens max: 47 tokens	min: 7 tokens mean: 16.5 tokens max: 47 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: MatryoshkaLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "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: 6
per_device_eval_batch_size: 6
num_train_epochs: 8
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 6
per_device_eval_batch_size: 6
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_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: 8
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
eval_on_start: False
eval_use_gather_object: False
batch_sampler: batch_sampler
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
1.0417	500	21.1353	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
2.0833	1000	20.7941	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
3.125	1500	20.7823	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
4.1667	2000	20.781	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
5.2083	2500	20.7707	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
6.25	3000	20.7661	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
7.2917	3500	20.7719	20.8565	nan	nan	nan	nan	nan	-	-	-	-	-
8.0	3840	-	-	-	-	-	-	-	nan	nan	nan	nan	nan

Framework Versions

Python: 3.9.19
Sentence Transformers: 3.1.0.dev0
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.34.2
Datasets: 2.21.0
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}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}

Downloads last month: -

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for dipteshkanojia/xlm-roberta-large-sts-matryoshka

Base model

FacebookAI/xlm-roberta-large

Finetuned

(755)

this model

Dataset used to train dipteshkanojia/xlm-roberta-large-sts-matryoshka

Evaluation results

Pearson Cosine on sts dev 768
self-reported

NaN
Spearman Cosine on sts dev 768
self-reported

NaN
Pearson Manhattan on sts dev 768
self-reported

-0.038
Spearman Manhattan on sts dev 768
self-reported

-0.031
Pearson Euclidean on sts dev 768
self-reported

-0.074
Spearman Euclidean on sts dev 768
self-reported

-0.016
Pearson Dot on sts dev 768
self-reported

-0.053
Spearman Dot on sts dev 768
self-reported

-0.039
Pearson Max on sts dev 768
self-reported

NaN
Spearman Max on sts dev 768
self-reported

NaN

View on Papers With Code