SentenceTransformer based on l3cube-pune/indic-sentence-similarity-sbert

This is a sentence-transformers model finetuned from l3cube-pune/indic-sentence-similarity-sbert 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: l3cube-pune/indic-sentence-similarity-sbert
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: BertModel 
  (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("ammumadhu/indic-bert-nli-matryoshka")
# Run inference
sentences = [
    'Then he ran.',
    'He then started to run.',
    'A man plays the flute.',
]
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	0.8609
spearman_cosine	0.8663
pearson_manhattan	0.8587
spearman_manhattan	0.8612
pearson_euclidean	0.8585
spearman_euclidean	0.8611
pearson_dot	0.8259
spearman_dot	0.826
pearson_max	0.8609
spearman_max	0.8663

Semantic Similarity

Dataset: sts-dev-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8594
spearman_cosine	0.8649
pearson_manhattan	0.8574
spearman_manhattan	0.8599
pearson_euclidean	0.8575
spearman_euclidean	0.8601
pearson_dot	0.8223
spearman_dot	0.8227
pearson_max	0.8594
spearman_max	0.8649

Semantic Similarity

Dataset: sts-dev-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8506
spearman_cosine	0.8576
pearson_manhattan	0.8528
spearman_manhattan	0.8553
pearson_euclidean	0.8527
spearman_euclidean	0.8551
pearson_dot	0.7944
spearman_dot	0.7964
pearson_max	0.8528
spearman_max	0.8576

Semantic Similarity

Dataset: sts-dev-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8411
spearman_cosine	0.8505
pearson_manhattan	0.8462
spearman_manhattan	0.849
pearson_euclidean	0.8458
spearman_euclidean	0.8487
pearson_dot	0.7756
spearman_dot	0.7756
pearson_max	0.8462
spearman_max	0.8505

Semantic Similarity

Dataset: sts-dev-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8177
spearman_cosine	0.8308
pearson_manhattan	0.8292
spearman_manhattan	0.832
pearson_euclidean	0.8311
spearman_euclidean	0.8334
pearson_dot	0.7153
spearman_dot	0.7181
pearson_max	0.8311
spearman_max	0.8334

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8492
spearman_cosine	0.8569
pearson_manhattan	0.8572
spearman_manhattan	0.8566
pearson_euclidean	0.8569
spearman_euclidean	0.8567
pearson_dot	0.7969
spearman_dot	0.7879
pearson_max	0.8572
spearman_max	0.8569

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8507
spearman_cosine	0.8575
pearson_manhattan	0.8564
spearman_manhattan	0.856
pearson_euclidean	0.8562
spearman_euclidean	0.8561
pearson_dot	0.7973
spearman_dot	0.7873
pearson_max	0.8564
spearman_max	0.8575

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8467
spearman_cosine	0.8523
pearson_manhattan	0.8516
spearman_manhattan	0.8516
pearson_euclidean	0.8506
spearman_euclidean	0.8504
pearson_dot	0.7757
spearman_dot	0.7687
pearson_max	0.8516
spearman_max	0.8523

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8377
spearman_cosine	0.8472
pearson_manhattan	0.8466
spearman_manhattan	0.8488
pearson_euclidean	0.8456
spearman_euclidean	0.8472
pearson_dot	0.7503
spearman_dot	0.7416
pearson_max	0.8466
spearman_max	0.8488

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8174
spearman_cosine	0.8316
pearson_manhattan	0.832
spearman_manhattan	0.8347
pearson_euclidean	0.8335
spearman_euclidean	0.8351
pearson_dot	0.6935
spearman_dot	0.6844
pearson_max	0.8335
spearman_max	0.8351

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: 18.8 tokens max: 89 tokens	min: 4 tokens mean: 11.84 tokens max: 36 tokens	min: 4 tokens mean: 12.39 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: 18.54 tokens max: 74 tokens	min: 4 tokens mean: 9.97 tokens max: 30 tokens	min: 5 tokens mean: 10.59 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	7.9432	4.2806	0.8509	0.8570	0.8633	0.8311	0.8644	-	-	-	-	-
0.7595	60	6.1701	3.9498	0.8505	0.8576	0.8649	0.8308	0.8663	-	-	-	-	-
1.0	79	-	-	-	-	-	-	-	0.8472	0.8523	0.8575	0.8316	0.8569

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: 2.19.2
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",
}

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}
}

Downloads last month: 5

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for ammumadhu/indic-bert-nli-matryoshka

Base model

l3cube-pune/indic-sentence-similarity-sbert

Finetuned

(2)

this model

Evaluation results

Pearson Cosine on sts dev 768
self-reported

0.861
Spearman Cosine on sts dev 768
self-reported

0.866
Pearson Manhattan on sts dev 768
self-reported

0.859
Spearman Manhattan on sts dev 768
self-reported

0.861
Pearson Euclidean on sts dev 768
self-reported

0.858
Spearman Euclidean on sts dev 768
self-reported

0.861
Pearson Dot on sts dev 768
self-reported

0.826
Spearman Dot on sts dev 768
self-reported

0.826
Pearson Max on sts dev 768
self-reported

0.861
Spearman Max on sts dev 768
self-reported

0.866