metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:557850
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: >-
      Mwanamume aliyepangwa vizuri anasimama kwa mguu mmoja karibu na pwani safi
      ya bahari.
    sentences:
      - mtu anacheka wakati wa kufua nguo
      - Mwanamume fulani yuko nje karibu na ufuo wa bahari.
      - Mwanamume fulani ameketi kwenye sofa yake.
  - source_sentence: >-
      Mwanamume mwenye ngozi nyeusi akivuta sigareti karibu na chombo cha taka
      cha kijani.
    sentences:
      - Karibu na chombo cha taka mwanamume huyo alisimama na kuvuta sigareti
      - Kitanda ni chafu.
      - >-
        Alipokuwa kwenye dimbwi la kuogelea mvulana huyo mwenye ugonjwa wa
        albino alijihadhari na jua kupita kiasi
  - source_sentence: >-
      Mwanamume kijana mwenye nywele nyekundu anaketi ukutani akisoma gazeti
      huku mwanamke na msichana mchanga wakipita.
    sentences:
      - >-
        Mwanamume aliyevalia shati la bluu amegonga ukuta kando ya barabara na
        gari la bluu na gari nyekundu lenye maji nyuma.
      - >-
        Mwanamume mchanga anatazama gazeti huku wanawake wawili wakipita karibu
        naye.
      - >-
        Mwanamume huyo mchanga analala huku Mama akimwongoza binti yake kwenye
        bustani.
  - source_sentence: Wasichana wako nje.
    sentences:
      - Wasichana wawili wakisafiri kwenye sehemu ya kusisimua.
      - >-
        Kuna watu watatu wakiongoza gari linaloweza kugeuzwa-geuzwa wakipita
        watu wengine.
      - >-
        Wasichana watatu wamesimama pamoja katika chumba, mmoja anasikiliza,
        mwingine anaandika ukutani na wa tatu anaongea nao.
  - source_sentence: >-
      Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini
      kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye
      mojawapo ya miguu ya benchi.
    sentences:
      - Mwanamume amelala uso chini kwenye benchi ya bustani.
      - Mwanamke anaunganisha uzi katika mipira kando ya rundo la mipira
      - Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.6942864389866223
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6856061049537777
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6885375818451587
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6872214410233022
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6914785578290242
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6905722127311041
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6799233396985102
            name: Pearson Dot
          - type: spearman_dot
            value: 0.667743621858275
            name: Spearman Dot
          - type: pearson_max
            value: 0.6942864389866223
            name: Pearson Max
          - type: spearman_max
            value: 0.6905722127311041
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.6891584502617563
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6814103986417178
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6968187377070036
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6920002958564649
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7000628001426884
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6960243670969477
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6364862920838279
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6189765115954626
            name: Spearman Dot
          - type: pearson_max
            value: 0.7000628001426884
            name: Pearson Max
          - type: spearman_max
            value: 0.6960243670969477
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.6782226699898293
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6755345411699644
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6962074727926596
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.689094339218281
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6996133052307816
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6937517032138506
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.58122590177631
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5606971476688047
            name: Spearman Dot
          - type: pearson_max
            value: 0.6996133052307816
            name: Pearson Max
          - type: spearman_max
            value: 0.6937517032138506
            name: Spearman Max

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 tokens
Similarity Function: Cosine Similarity

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (2): Normalize()
)

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("Mollel/swahili-all-MiniLM-L6-v2-nli-matryoshka")
# Run inference
sentences = [
    'Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo ya miguu ya benchi.',
    'Mwanamume amelala uso chini kwenye benchi ya bustani.',
    'Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6943
spearman_cosine	0.6856
pearson_manhattan	0.6885
spearman_manhattan	0.6872
pearson_euclidean	0.6915
spearman_euclidean	0.6906
pearson_dot	0.6799
spearman_dot	0.6677
pearson_max	0.6943
spearman_max	0.6906

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6892
spearman_cosine	0.6814
pearson_manhattan	0.6968
spearman_manhattan	0.692
pearson_euclidean	0.7001
spearman_euclidean	0.696
pearson_dot	0.6365
spearman_dot	0.619
pearson_max	0.7001
spearman_max	0.696

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6782
spearman_cosine	0.6755
pearson_manhattan	0.6962
spearman_manhattan	0.6891
pearson_euclidean	0.6996
spearman_euclidean	0.6938
pearson_dot	0.5812
spearman_dot	0.5607
pearson_max	0.6996
spearman_max	0.6938

Training Details

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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
prediction_loss_only: True
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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, '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_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	sts-test-128_spearman_cosine	sts-test-256_spearman_cosine	sts-test-64_spearman_cosine
0.0229	100	12.9498	-	-	-
0.0459	200	9.9003	-	-	-
0.0688	300	8.6333	-	-	-
0.0918	400	8.0124	-	-	-
0.1147	500	7.2322	-	-	-
0.1376	600	6.936	-	-	-
0.1606	700	7.2855	-	-	-
0.1835	800	6.5985	-	-	-
0.2065	900	6.4369	-	-	-
0.2294	1000	6.2767	-	-	-
0.2524	1100	6.4011	-	-	-
0.2753	1200	6.1288	-	-	-
0.2982	1300	6.1466	-	-	-
0.3212	1400	5.9279	-	-	-
0.3441	1500	5.8959	-	-	-
0.3671	1600	5.5911	-	-	-
0.3900	1700	5.5258	-	-	-
0.4129	1800	5.5835	-	-	-
0.4359	1900	5.4701	-	-	-
0.4588	2000	5.3888	-	-	-
0.4818	2100	5.4474	-	-	-
0.5047	2200	5.1465	-	-	-
0.5276	2300	5.28	-	-	-
0.5506	2400	5.4184	-	-	-
0.5735	2500	5.3811	-	-	-
0.5965	2600	5.2171	-	-	-
0.6194	2700	5.3212	-	-	-
0.6423	2800	5.2493	-	-	-
0.6653	2900	5.459	-	-	-
0.6882	3000	5.068	-	-	-
0.7112	3100	5.1415	-	-	-
0.7341	3200	5.0764	-	-	-
0.7571	3300	6.1606	-	-	-
0.7800	3400	6.1028	-	-	-
0.8029	3500	5.7441	-	-	-
0.8259	3600	5.7148	-	-	-
0.8488	3700	5.4799	-	-	-
0.8718	3800	5.4396	-	-	-
0.8947	3900	5.3519	-	-	-
0.9176	4000	5.2394	-	-	-
0.9406	4100	5.2311	-	-	-
0.9635	4200	5.3486	-	-	-
0.9865	4300	5.215	-	-	-
1.0	4359	-	0.6814	0.6856	0.6755

Framework Versions

Python: 3.11.9
Sentence Transformers: 3.0.1
Transformers: 4.40.1
PyTorch: 2.3.0+cu121
Accelerate: 0.29.3
Datasets: 2.19.0
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}
}

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}
}