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/paraphrase-multilingual-mpnet-base-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/paraphrase-multilingual-mpnet-base-v2
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 768
type: sts-test-768
metrics:
- type: pearson_cosine
value: 0.7073072916945755
name: Pearson Cosine
- type: spearman_cosine
value: 0.7038302407401268
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6971720016143421
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6937589389074208
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6995677027369716
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6964739266023146
name: Spearman Euclidean
- type: pearson_dot
value: 0.610950397941133
name: Pearson Dot
- type: spearman_dot
value: 0.593970670155461
name: Spearman Dot
- type: pearson_max
value: 0.7073072916945755
name: Pearson Max
- type: spearman_max
value: 0.7038302407401268
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 512
type: sts-test-512
metrics:
- type: pearson_cosine
value: 0.7045540268598433
name: Pearson Cosine
- type: spearman_cosine
value: 0.7023621139637947
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6975397258794529
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6927560109749419
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6985549032977664
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6941789537125014
name: Spearman Euclidean
- type: pearson_dot
value: 0.582046017636523
name: Pearson Dot
- type: spearman_dot
value: 0.565355081915806
name: Spearman Dot
- type: pearson_max
value: 0.7045540268598433
name: Pearson Max
- type: spearman_max
value: 0.7023621139637947
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 256
type: sts-test-256
metrics:
- type: pearson_cosine
value: 0.7012922000956245
name: Pearson Cosine
- type: spearman_cosine
value: 0.7016107934280537
name: Spearman Cosine
- type: pearson_manhattan
value: 0.69508092429561
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6879849400335534
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6956451936598814
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6890266593479353
name: Spearman Euclidean
- type: pearson_dot
value: 0.5501625376986127
name: Pearson Dot
- type: spearman_dot
value: 0.5332005894675337
name: Spearman Dot
- type: pearson_max
value: 0.7012922000956245
name: Pearson Max
- type: spearman_max
value: 0.7016107934280537
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 128
type: sts-test-128
metrics:
- type: pearson_cosine
value: 0.6980581280594836
name: Pearson Cosine
- type: spearman_cosine
value: 0.7000311940508227
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6910651227829323
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6823572623875095
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6922658508243149
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6838439746630024
name: Spearman Euclidean
- type: pearson_dot
value: 0.5156063038618797
name: Pearson Dot
- type: spearman_dot
value: 0.5006742054178095
name: Spearman Dot
- type: pearson_max
value: 0.6980581280594836
name: Pearson Max
- type: spearman_max
value: 0.7000311940508227
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 64
type: sts-test-64
metrics:
- type: pearson_cosine
value: 0.6865218902262467
name: Pearson Cosine
- type: spearman_cosine
value: 0.6901005120722546
name: Spearman Cosine
- type: pearson_manhattan
value: 0.681113101036276
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6713556700583071
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6816926483485075
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6701163777153826
name: Spearman Euclidean
- type: pearson_dot
value: 0.4686654293362901
name: Pearson Dot
- type: spearman_dot
value: 0.4520420017929889
name: Spearman Dot
- type: pearson_max
value: 0.6865218902262467
name: Pearson Max
- type: spearman_max
value: 0.6901005120722546
name: Spearman Max
SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-mpnet-base-v2. 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 Sources
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(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
model = SentenceTransformer("sartifyllc/swahili-paraphrase-multilingual-mpnet-base-v2-nli-matryoshka")
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)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
Evaluation
Metrics
Semantic Similarity
Metric |
Value |
pearson_cosine |
0.7073 |
spearman_cosine |
0.7038 |
pearson_manhattan |
0.6972 |
spearman_manhattan |
0.6938 |
pearson_euclidean |
0.6996 |
spearman_euclidean |
0.6965 |
pearson_dot |
0.611 |
spearman_dot |
0.594 |
pearson_max |
0.7073 |
spearman_max |
0.7038 |
Semantic Similarity
Metric |
Value |
pearson_cosine |
0.7046 |
spearman_cosine |
0.7024 |
pearson_manhattan |
0.6975 |
spearman_manhattan |
0.6928 |
pearson_euclidean |
0.6986 |
spearman_euclidean |
0.6942 |
pearson_dot |
0.582 |
spearman_dot |
0.5654 |
pearson_max |
0.7046 |
spearman_max |
0.7024 |
Semantic Similarity
Metric |
Value |
pearson_cosine |
0.7013 |
spearman_cosine |
0.7016 |
pearson_manhattan |
0.6951 |
spearman_manhattan |
0.688 |
pearson_euclidean |
0.6956 |
spearman_euclidean |
0.689 |
pearson_dot |
0.5502 |
spearman_dot |
0.5332 |
pearson_max |
0.7013 |
spearman_max |
0.7016 |
Semantic Similarity
Metric |
Value |
pearson_cosine |
0.6981 |
spearman_cosine |
0.7 |
pearson_manhattan |
0.6911 |
spearman_manhattan |
0.6824 |
pearson_euclidean |
0.6923 |
spearman_euclidean |
0.6838 |
pearson_dot |
0.5156 |
spearman_dot |
0.5007 |
pearson_max |
0.6981 |
spearman_max |
0.7 |
Semantic Similarity
Metric |
Value |
pearson_cosine |
0.6865 |
spearman_cosine |
0.6901 |
pearson_manhattan |
0.6811 |
spearman_manhattan |
0.6714 |
pearson_euclidean |
0.6817 |
spearman_euclidean |
0.6701 |
pearson_dot |
0.4687 |
spearman_dot |
0.452 |
pearson_max |
0.6865 |
spearman_max |
0.6901 |
Training Details
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size
: 16
per_device_eval_batch_size
: 16
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
: 16
per_device_eval_batch_size
: 16
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
Click to expand
Epoch |
Step |
Training Loss |
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 |
0.0057 |
100 |
18.7677 |
- |
- |
- |
- |
- |
0.0115 |
200 |
10.5065 |
- |
- |
- |
- |
- |
0.0172 |
300 |
8.0917 |
- |
- |
- |
- |
- |
0.0229 |
400 |
8.4617 |
- |
- |
- |
- |
- |
0.0287 |
500 |
8.0789 |
- |
- |
- |
- |
- |
0.0344 |
600 |
7.3287 |
- |
- |
- |
- |
- |
0.0402 |
700 |
6.3282 |
- |
- |
- |
- |
- |
0.0459 |
800 |
5.5327 |
- |
- |
- |
- |
- |
0.0516 |
900 |
5.7985 |
- |
- |
- |
- |
- |
0.0574 |
1000 |
6.1129 |
- |
- |
- |
- |
- |
0.0631 |
1100 |
6.1784 |
- |
- |
- |
- |
- |
0.0688 |
1200 |
6.3647 |
- |
- |
- |
- |
- |
0.0746 |
1300 |
7.4443 |
- |
- |
- |
- |
- |
0.0803 |
1400 |
6.6881 |
- |
- |
- |
- |
- |
0.0860 |
1500 |
6.09 |
- |
- |
- |
- |
- |
0.0918 |
1600 |
5.4176 |
- |
- |
- |
- |
- |
0.0975 |
1700 |
5.4563 |
- |
- |
- |
- |
- |
0.1033 |
1800 |
5.7071 |
- |
- |
- |
- |
- |
0.1090 |
1900 |
7.0201 |
- |
- |
- |
- |
- |
0.1147 |
2000 |
6.2688 |
- |
- |
- |
- |
- |
0.1205 |
2100 |
6.1499 |
- |
- |
- |
- |
- |
0.1262 |
2200 |
5.947 |
- |
- |
- |
- |
- |
0.1319 |
2300 |
5.5437 |
- |
- |
- |
- |
- |
0.1377 |
2400 |
5.4958 |
- |
- |
- |
- |
- |
0.1434 |
2500 |
5.5032 |
- |
- |
- |
- |
- |
0.1491 |
2600 |
4.8026 |
- |
- |
- |
- |
- |
0.1549 |
2700 |
5.0879 |
- |
- |
- |
- |
- |
0.1606 |
2800 |
5.6166 |
- |
- |
- |
- |
- |
0.1664 |
2900 |
5.8146 |
- |
- |
- |
- |
- |
0.1721 |
3000 |
6.4168 |
- |
- |
- |
- |
- |
0.1778 |
3100 |
6.5094 |
- |
- |
- |
- |
- |
0.1836 |
3200 |
5.9273 |
- |
- |
- |
- |
- |
0.1893 |
3300 |
5.6202 |
- |
- |
- |
- |
- |
0.1950 |
3400 |
5.1419 |
- |
- |
- |
- |
- |
0.2008 |
3500 |
5.9303 |
- |
- |
- |
- |
- |
0.2065 |
3600 |
5.3225 |
- |
- |
- |
- |
- |
0.2122 |
3700 |
5.5183 |
- |
- |
- |
- |
- |
0.2180 |
3800 |
5.6644 |
- |
- |
- |
- |
- |
0.2237 |
3900 |
6.2006 |
- |
- |
- |
- |
- |
0.2294 |
4000 |
5.8684 |
- |
- |
- |
- |
- |
0.2352 |
4100 |
5.5406 |
- |
- |
- |
- |
- |
0.2409 |
4200 |
5.1763 |
- |
- |
- |
- |
- |
0.2467 |
4300 |
5.7639 |
- |
- |
- |
- |
- |
0.2524 |
4400 |
5.8734 |
- |
- |
- |
- |
- |
0.2581 |
4500 |
6.0215 |
- |
- |
- |
- |
- |
0.2639 |
4600 |
5.5183 |
- |
- |
- |
- |
- |
0.2696 |
4700 |
5.5938 |
- |
- |
- |
- |
- |
0.2753 |
4800 |
5.6869 |
- |
- |
- |
- |
- |
0.2811 |
4900 |
5.1235 |
- |
- |
- |
- |
- |
0.2868 |
5000 |
5.189 |
- |
- |
- |
- |
- |
0.2925 |
5100 |
5.081 |
- |
- |
- |
- |
- |
0.2983 |
5200 |
5.4992 |
- |
- |
- |
- |
- |
0.3040 |
5300 |
5.6662 |
- |
- |
- |
- |
- |
0.3098 |
5400 |
5.5772 |
- |
- |
- |
- |
- |
0.3155 |
5500 |
5.3595 |
- |
- |
- |
- |
- |
0.3212 |
5600 |
4.805 |
- |
- |
- |
- |
- |
0.3270 |
5700 |
5.1821 |
- |
- |
- |
- |
- |
0.3327 |
5800 |
5.3221 |
- |
- |
- |
- |
- |
0.3384 |
5900 |
5.4223 |
- |
- |
- |
- |
- |
0.3442 |
6000 |
5.2718 |
- |
- |
- |
- |
- |
0.3499 |
6100 |
5.2213 |
- |
- |
- |
- |
- |
0.3556 |
6200 |
5.5453 |
- |
- |
- |
- |
- |
0.3614 |
6300 |
4.8502 |
- |
- |
- |
- |
- |
0.3671 |
6400 |
4.8912 |
- |
- |
- |
- |
- |
0.3729 |
6500 |
4.8791 |
- |
- |
- |
- |
- |
0.3786 |
6600 |
5.2418 |
- |
- |
- |
- |
- |
0.3843 |
6700 |
4.7621 |
- |
- |
- |
- |
- |
0.3901 |
6800 |
4.9017 |
- |
- |
- |
- |
- |
0.3958 |
6900 |
4.8965 |
- |
- |
- |
- |
- |
0.4015 |
7000 |
4.6081 |
- |
- |
- |
- |
- |
0.4073 |
7100 |
5.4256 |
- |
- |
- |
- |
- |
0.4130 |
7200 |
5.0878 |
- |
- |
- |
- |
- |
0.4187 |
7300 |
4.9899 |
- |
- |
- |
- |
- |
0.4245 |
7400 |
4.8508 |
- |
- |
- |
- |
- |
0.4302 |
7500 |
5.253 |
- |
- |
- |
- |
- |
0.4360 |
7600 |
4.8363 |
- |
- |
- |
- |
- |
0.4417 |
7700 |
4.5555 |
- |
- |
- |
- |
- |
0.4474 |
7800 |
4.9668 |
- |
- |
- |
- |
- |
0.4532 |
7900 |
5.1911 |
- |
- |
- |
- |
- |
0.4589 |
8000 |
4.468 |
- |
- |
- |
- |
- |
0.4646 |
8100 |
4.8253 |
- |
- |
- |
- |
- |
0.4704 |
8200 |
4.89 |
- |
- |
- |
- |
- |
0.4761 |
8300 |
4.5547 |
- |
- |
- |
- |
- |
0.4818 |
8400 |
4.9499 |
- |
- |
- |
- |
- |
0.4876 |
8500 |
4.777 |
- |
- |
- |
- |
- |
0.4933 |
8600 |
4.8066 |
- |
- |
- |
- |
- |
0.4991 |
8700 |
5.0615 |
- |
- |
- |
- |
- |
0.5048 |
8800 |
4.9215 |
- |
- |
- |
- |
- |
0.5105 |
8900 |
4.8484 |
- |
- |
- |
- |
- |
0.5163 |
9000 |
4.6272 |
- |
- |
- |
- |
- |
0.5220 |
9100 |
4.8225 |
- |
- |
- |
- |
- |
0.5277 |
9200 |
4.7131 |
- |
- |
- |
- |
- |
0.5335 |
9300 |
4.3969 |
- |
- |
- |
- |
- |
0.5392 |
9400 |
4.4143 |
- |
- |
- |
- |
- |
0.5449 |
9500 |
4.9588 |
- |
- |
- |
- |
- |
0.5507 |
9600 |
4.7358 |
- |
- |
- |
- |
- |
0.5564 |
9700 |
5.0527 |
- |
- |
- |
- |
- |
0.5622 |
9800 |
4.852 |
- |
- |
- |
- |
- |
0.5679 |
9900 |
5.0855 |
- |
- |
- |
- |
- |
0.5736 |
10000 |
4.8507 |
- |
- |
- |
- |
- |
0.5794 |
10100 |
4.8007 |
- |
- |
- |
- |
- |
0.5851 |
10200 |
4.7279 |
- |
- |
- |
- |
- |
0.5908 |
10300 |
5.0171 |
- |
- |
- |
- |
- |
0.5966 |
10400 |
4.5288 |
- |
- |
- |
- |
- |
0.6023 |
10500 |
4.4488 |
- |
- |
- |
- |
- |
0.6080 |
10600 |
4.6557 |
- |
- |
- |
- |
- |
0.6138 |
10700 |
4.6881 |
- |
- |
- |
- |
- |
0.6195 |
10800 |
5.0514 |
- |
- |
- |
- |
- |
0.6253 |
10900 |
4.6301 |
- |
- |
- |
- |
- |
0.6310 |
11000 |
4.8233 |
- |
- |
- |
- |
- |
0.6367 |
11100 |
5.0136 |
- |
- |
- |
- |
- |
0.6425 |
11200 |
4.3774 |
- |
- |
- |
- |
- |
0.6482 |
11300 |
5.1213 |
- |
- |
- |
- |
- |
0.6539 |
11400 |
4.528 |
- |
- |
- |
- |
- |
0.6597 |
11500 |
4.8555 |
- |
- |
- |
- |
- |
0.6654 |
11600 |
4.2198 |
- |
- |
- |
- |
- |
0.6711 |
11700 |
5.0931 |
- |
- |
- |
- |
- |
0.6769 |
11800 |
4.9511 |
- |
- |
- |
- |
- |
0.6826 |
11900 |
4.5414 |
- |
- |
- |
- |
- |
0.6883 |
12000 |
4.5039 |
- |
- |
- |
- |
- |
0.6941 |
12100 |
4.8238 |
- |
- |
- |
- |
- |
0.6998 |
12200 |
4.6237 |
- |
- |
- |
- |
- |
0.7056 |
12300 |
4.6771 |
- |
- |
- |
- |
- |
0.7113 |
12400 |
4.6187 |
- |
- |
- |
- |
- |
0.7170 |
12500 |
4.4485 |
- |
- |
- |
- |
- |
0.7228 |
12600 |
4.2029 |
- |
- |
- |
- |
- |
0.7285 |
12700 |
4.5829 |
- |
- |
- |
- |
- |
0.7342 |
12800 |
4.617 |
- |
- |
- |
- |
- |
0.7400 |
12900 |
4.5606 |
- |
- |
- |
- |
- |
0.7457 |
13000 |
4.5745 |
- |
- |
- |
- |
- |
0.7514 |
13100 |
4.1457 |
- |
- |
- |
- |
- |
0.7572 |
13200 |
7.2499 |
- |
- |
- |
- |
- |
0.7629 |
13300 |
6.3681 |
- |
- |
- |
- |
- |
0.7687 |
13400 |
6.2052 |
- |
- |
- |
- |
- |
0.7744 |
13500 |
5.9569 |
- |
- |
- |
- |
- |
0.7801 |
13600 |
5.2649 |
- |
- |
- |
- |
- |
0.7859 |
13700 |
5.5198 |
- |
- |
- |
- |
- |
0.7916 |
13800 |
5.2808 |
- |
- |
- |
- |
- |
0.7973 |
13900 |
5.1534 |
- |
- |
- |
- |
- |
0.8031 |
14000 |
4.7831 |
- |
- |
- |
- |
- |
0.8088 |
14100 |
4.5975 |
- |
- |
- |
- |
- |
0.8145 |
14200 |
4.6134 |
- |
- |
- |
- |
- |
0.8203 |
14300 |
4.5497 |
- |
- |
- |
- |
- |
0.8260 |
14400 |
4.6003 |
- |
- |
- |
- |
- |
0.8318 |
14500 |
4.7011 |
- |
- |
- |
- |
- |
0.8375 |
14600 |
4.4208 |
- |
- |
- |
- |
- |
0.8432 |
14700 |
4.4052 |
- |
- |
- |
- |
- |
0.8490 |
14800 |
4.1121 |
- |
- |
- |
- |
- |
0.8547 |
14900 |
4.2418 |
- |
- |
- |
- |
- |
0.8604 |
15000 |
4.2314 |
- |
- |
- |
- |
- |
0.8662 |
15100 |
3.8679 |
- |
- |
- |
- |
- |
0.8719 |
15200 |
4.0173 |
- |
- |
- |
- |
- |
0.8776 |
15300 |
4.0758 |
- |
- |
- |
- |
- |
0.8834 |
15400 |
3.8581 |
- |
- |
- |
- |
- |
0.8891 |
15500 |
4.0601 |
- |
- |
- |
- |
- |
0.8949 |
15600 |
3.8738 |
- |
- |
- |
- |
- |
0.9006 |
15700 |
4.0744 |
- |
- |
- |
- |
- |
0.9063 |
15800 |
3.917 |
- |
- |
- |
- |
- |
0.9121 |
15900 |
3.7996 |
- |
- |
- |
- |
- |
0.9178 |
16000 |
3.7511 |
- |
- |
- |
- |
- |
0.9235 |
16100 |
3.7654 |
- |
- |
- |
- |
- |
0.9293 |
16200 |
3.6185 |
- |
- |
- |
- |
- |
0.9350 |
16300 |
3.5877 |
- |
- |
- |
- |
- |
0.9407 |
16400 |
3.8974 |
- |
- |
- |
- |
- |
0.9465 |
16500 |
3.5654 |
- |
- |
- |
- |
- |
0.9522 |
16600 |
3.6 |
- |
- |
- |
- |
- |
0.9580 |
16700 |
3.6468 |
- |
- |
- |
- |
- |
0.9637 |
16800 |
3.7221 |
- |
- |
- |
- |
- |
0.9694 |
16900 |
3.5939 |
- |
- |
- |
- |
- |
0.9752 |
17000 |
3.8597 |
- |
- |
- |
- |
- |
0.9809 |
17100 |
3.6323 |
- |
- |
- |
- |
- |
0.9866 |
17200 |
3.5251 |
- |
- |
- |
- |
- |
0.9924 |
17300 |
3.6949 |
- |
- |
- |
- |
- |
0.9981 |
17400 |
3.5682 |
- |
- |
- |
- |
- |
1.0 |
17433 |
- |
0.7000 |
0.7016 |
0.7024 |
0.6901 |
0.7038 |
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}
}