metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1115700
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: nomic-ai/nomic-embed-text-v1.5
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: Ndege mwenye mdomo mrefu katikati ya ndege.
    sentences:
      - Panya anayekimbia juu ya gurudumu.
      - Mtu anashindana katika mashindano ya mbio.
      - Ndege anayeruka.
  - source_sentence: >-
      Msichana mchanga mwenye nywele nyeusi anakabili kamera na kushikilia mfuko
      wa karatasi wakati amevaa shati la machungwa na mabawa ya kipepeo yenye
      rangi nyingi.
    sentences:
      - Mwanamke mzee anakataa kupigwa picha.
      - mtu akila na mvulana mdogo kwenye kijia cha jiji
      - Msichana mchanga anakabili kamera.
  - source_sentence: >-
      Wanawake na watoto wameketi nje katika kivuli wakati kikundi cha watoto
      wadogo wameketi ndani katika kivuli.
    sentences:
      - Mwanamke na watoto na kukaa chini.
      - Mwanamke huyo anakimbia.
      - Watu wanasafiri kwa baiskeli.
  - source_sentence: >-
      Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi ya
      kuogelea akiwa kwenye dimbwi.
    sentences:
      - >-
        Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye
        dimbwi.
      - Someone is holding oranges and walking
      - Mama na binti wakinunua viatu.
  - source_sentence: >-
      Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu
      kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au
      wameketi nyuma.
    sentences:
      - tai huruka
      - mwanamume na mwanamke wenye mikoba
      - Wanaume wawili wameketi karibu na mwanamke.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.6944960057464138
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6872396378196957
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7086043588614903
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7136479613274518
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7084460037709435
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7128357831285198
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.481902874304561
            name: Pearson Dot
          - type: spearman_dot
            value: 0.46588918379526945
            name: Spearman Dot
          - type: pearson_max
            value: 0.7086043588614903
            name: Pearson Max
          - type: spearman_max
            value: 0.7136479613274518
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.6925787246105148
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6859479129419207
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7087290093387656
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7127968133455542
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7088805484816247
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7123606046721803
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4684333245586192
            name: Pearson Dot
          - type: spearman_dot
            value: 0.45257836578849003
            name: Spearman Dot
          - type: pearson_max
            value: 0.7088805484816247
            name: Pearson Max
          - type: spearman_max
            value: 0.7127968133455542
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.6876956481856266
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6814892249857147
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7083882582081078
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7097524143994903
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7094190252305796
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7104287347206688
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4438925722484721
            name: Pearson Dot
          - type: spearman_dot
            value: 0.4255299982188107
            name: Spearman Dot
          - type: pearson_max
            value: 0.7094190252305796
            name: Pearson Max
          - type: spearman_max
            value: 0.7104287347206688
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.6708560165075523
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6669935075512006
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7041961281711793
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7000807688296651
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7055061381768357
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7022686907818495
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.37855771167572094
            name: Pearson Dot
          - type: spearman_dot
            value: 0.35930717422088765
            name: Spearman Dot
          - type: pearson_max
            value: 0.7055061381768357
            name: Pearson Max
          - type: spearman_max
            value: 0.7022686907818495
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.6533817775144477
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6523997361414113
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6919834348567717
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6857245312336051
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6950438027503257
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6899151458827059
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.33502302384042637
            name: Pearson Dot
          - type: spearman_dot
            value: 0.3097469345046609
            name: Spearman Dot
          - type: pearson_max
            value: 0.6950438027503257
            name: Pearson Max
          - type: spearman_max
            value: 0.6899151458827059
            name: Spearman Max

SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5

This is a sentence-transformers model finetuned from nomic-ai/nomic-embed-text-v1.5 on the Mollel/swahili-n_li-triplet-swh-eng 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: nomic-ai/nomic-embed-text-v1.5
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- Mollel/swahili-n_li-triplet-swh-eng

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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel 
  (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("Mollel/MultiLinguSwahili-nomic-embed-text-v1.5-nli-matryoshka")
# Run inference
sentences = [
    'Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.',
    'mwanamume na mwanamke wenye mikoba',
    'tai huruka',
]
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-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6945
spearman_cosine	0.6872
pearson_manhattan	0.7086
spearman_manhattan	0.7136
pearson_euclidean	0.7084
spearman_euclidean	0.7128
pearson_dot	0.4819
spearman_dot	0.4659
pearson_max	0.7086
spearman_max	0.7136

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6926
spearman_cosine	0.6859
pearson_manhattan	0.7087
spearman_manhattan	0.7128
pearson_euclidean	0.7089
spearman_euclidean	0.7124
pearson_dot	0.4684
spearman_dot	0.4526
pearson_max	0.7089
spearman_max	0.7128

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6877
spearman_cosine	0.6815
pearson_manhattan	0.7084
spearman_manhattan	0.7098
pearson_euclidean	0.7094
spearman_euclidean	0.7104
pearson_dot	0.4439
spearman_dot	0.4255
pearson_max	0.7094
spearman_max	0.7104

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6709
spearman_cosine	0.667
pearson_manhattan	0.7042
spearman_manhattan	0.7001
pearson_euclidean	0.7055
spearman_euclidean	0.7023
pearson_dot	0.3786
spearman_dot	0.3593
pearson_max	0.7055
spearman_max	0.7023

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6534
spearman_cosine	0.6524
pearson_manhattan	0.692
spearman_manhattan	0.6857
pearson_euclidean	0.695
spearman_euclidean	0.6899
pearson_dot	0.335
spearman_dot	0.3097
pearson_max	0.695
spearman_max	0.6899

Training Details

Training Dataset

Mollel/swahili-n_li-triplet-swh-eng

Dataset: Mollel/swahili-n_li-triplet-swh-eng
Size: 1,115,700 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: 15.18 tokens max: 80 tokens	min: 5 tokens mean: 18.53 tokens max: 52 tokens	min: 5 tokens mean: 17.8 tokens max: 53 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.`
`Mtu aliyepanda farasi anaruka juu ya ndege iliyovunjika.`	`Mtu yuko nje, juu ya farasi.`	`Mtu yuko kwenye mkahawa, akiagiza omelette.`
`Children smiling and waving at camera`	`There are children present`	`The kids are frowning`

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

Mollel/swahili-n_li-triplet-swh-eng

Dataset: Mollel/swahili-n_li-triplet-swh-eng
Size: 13,168 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: 26.43 tokens max: 94 tokens	min: 5 tokens mean: 13.37 tokens max: 65 tokens	min: 5 tokens mean: 14.7 tokens max: 54 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.`
`Wanawake wawili wanakumbatiana huku wakishikilia vifurushi vya kwenda.`	`Wanawake wawili wanashikilia vifurushi.`	`Wanaume hao wanapigana nje ya duka la vyakula vitamu.`
`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.`

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

per_device_train_batch_size: 24
per_device_eval_batch_size: 24
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
bf16: 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: 24
per_device_eval_batch_size: 24
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 2e-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: True
fp16: False
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
0.0043	100	10.0627	-	-	-	-	-
0.0086	200	8.2355	-	-	-	-	-
0.0129	300	6.7233	-	-	-	-	-
0.0172	400	6.5832	-	-	-	-	-
0.0215	500	6.7512	-	-	-	-	-
0.0258	600	6.7634	-	-	-	-	-
0.0301	700	6.5592	-	-	-	-	-
0.0344	800	5.0689	-	-	-	-	-
0.0387	900	4.7079	-	-	-	-	-
0.0430	1000	4.6359	-	-	-	-	-
0.0473	1100	4.4513	-	-	-	-	-
0.0516	1200	4.2328	-	-	-	-	-
0.0559	1300	3.7454	-	-	-	-	-
0.0602	1400	3.9198	-	-	-	-	-
0.0645	1500	4.0727	-	-	-	-	-
0.0688	1600	3.8923	-	-	-	-	-
0.0731	1700	3.8137	-	-	-	-	-
0.0774	1800	4.1512	-	-	-	-	-
0.0817	1900	4.1304	-	-	-	-	-
0.0860	2000	4.0195	-	-	-	-	-
0.0903	2100	3.6836	-	-	-	-	-
0.0946	2200	2.9968	-	-	-	-	-
0.0990	2300	2.8909	-	-	-	-	-
0.1033	2400	3.0884	-	-	-	-	-
0.1076	2500	3.3081	-	-	-	-	-
0.1119	2600	3.6266	-	-	-	-	-
0.1162	2700	4.3754	-	-	-	-	-
0.1205	2800	4.0218	-	-	-	-	-
0.1248	2900	3.7167	-	-	-	-	-
0.1291	3000	3.4815	-	-	-	-	-
0.1334	3100	3.6446	-	-	-	-	-
0.1377	3200	3.44	-	-	-	-	-
0.1420	3300	3.6725	-	-	-	-	-
0.1463	3400	3.4699	-	-	-	-	-
0.1506	3500	3.076	-	-	-	-	-
0.1549	3600	3.1179	-	-	-	-	-
0.1592	3700	3.1704	-	-	-	-	-
0.1635	3800	3.4614	-	-	-	-	-
0.1678	3900	4.1157	-	-	-	-	-
0.1721	4000	4.1584	-	-	-	-	-
0.1764	4100	4.5602	-	-	-	-	-
0.1807	4200	3.6875	-	-	-	-	-
0.1850	4300	4.1521	-	-	-	-	-
0.1893	4400	3.5475	-	-	-	-	-
0.1936	4500	3.4036	-	-	-	-	-
0.1979	4600	3.0564	-	-	-	-	-
0.2022	4700	3.7761	-	-	-	-	-
0.2065	4800	3.6857	-	-	-	-	-
0.2108	4900	3.3534	-	-	-	-	-
0.2151	5000	4.1137	-	-	-	-	-
0.2194	5100	3.5239	-	-	-	-	-
0.2237	5200	4.1297	-	-	-	-	-
0.2280	5300	3.5339	-	-	-	-	-
0.2323	5400	3.9294	-	-	-	-	-
0.2366	5500	3.717	-	-	-	-	-
0.2409	5600	3.3346	-	-	-	-	-
0.2452	5700	4.0495	-	-	-	-	-
0.2495	5800	3.7869	-	-	-	-	-
0.2538	5900	3.9533	-	-	-	-	-
0.2581	6000	4.1135	-	-	-	-	-
0.2624	6100	3.6655	-	-	-	-	-
0.2667	6200	3.9111	-	-	-	-	-
0.2710	6300	3.8582	-	-	-	-	-
0.2753	6400	3.7712	-	-	-	-	-
0.2796	6500	3.6536	-	-	-	-	-
0.2839	6600	3.4516	-	-	-	-	-
0.2882	6700	3.7151	-	-	-	-	-
0.2925	6800	3.7659	-	-	-	-	-
0.2969	6900	3.3159	-	-	-	-	-
0.3012	7000	3.5753	-	-	-	-	-
0.3055	7100	4.2095	-	-	-	-	-
0.3098	7200	3.718	-	-	-	-	-
0.3141	7300	4.0709	-	-	-	-	-
0.3184	7400	3.8079	-	-	-	-	-
0.3227	7500	3.3735	-	-	-	-	-
0.3270	7600	3.7303	-	-	-	-	-
0.3313	7700	3.2693	-	-	-	-	-
0.3356	7800	3.6564	-	-	-	-	-
0.3399	7900	3.6702	-	-	-	-	-
0.3442	8000	3.7274	-	-	-	-	-
0.3485	8100	3.8536	-	-	-	-	-
0.3528	8200	3.9516	-	-	-	-	-
0.3571	8300	3.7351	-	-	-	-	-
0.3614	8400	3.649	-	-	-	-	-
0.3657	8500	3.5913	-	-	-	-	-
0.3700	8600	3.7733	-	-	-	-	-
0.3743	8700	3.6359	-	-	-	-	-
0.3786	8800	4.2983	-	-	-	-	-
0.3829	8900	3.6692	-	-	-	-	-
0.3872	9000	3.7309	-	-	-	-	-
0.3915	9100	3.8886	-	-	-	-	-
0.3958	9200	3.8999	-	-	-	-	-
0.4001	9300	3.5528	-	-	-	-	-
0.4044	9400	3.6309	-	-	-	-	-
0.4087	9500	4.2475	-	-	-	-	-
0.4130	9600	3.793	-	-	-	-	-
0.4173	9700	3.6575	-	-	-	-	-
0.4216	9800	3.84	-	-	-	-	-
0.4259	9900	3.3721	-	-	-	-	-
0.4302	10000	4.3743	-	-	-	-	-
0.4345	10100	3.5054	-	-	-	-	-
0.4388	10200	3.54	-	-	-	-	-
0.4431	10300	3.6197	-	-	-	-	-
0.4474	10400	3.7567	-	-	-	-	-
0.4517	10500	3.9814	-	-	-	-	-
0.4560	10600	3.6277	-	-	-	-	-
0.4603	10700	3.5071	-	-	-	-	-
0.4646	10800	3.8348	-	-	-	-	-
0.4689	10900	3.8674	-	-	-	-	-
0.4732	11000	3.0325	-	-	-	-	-
0.4775	11100	3.7262	-	-	-	-	-
0.4818	11200	3.6921	-	-	-	-	-
0.4861	11300	3.4946	-	-	-	-	-
0.4904	11400	3.7541	-	-	-	-	-
0.4948	11500	3.6751	-	-	-	-	-
0.4991	11600	3.8765	-	-	-	-	-
0.5034	11700	3.5058	-	-	-	-	-
0.5077	11800	3.5135	-	-	-	-	-
0.5120	11900	3.8052	-	-	-	-	-
0.5163	12000	3.3015	-	-	-	-	-
0.5206	12100	3.5389	-	-	-	-	-
0.5249	12200	3.5226	-	-	-	-	-
0.5292	12300	3.6715	-	-	-	-	-
0.5335	12400	3.2256	-	-	-	-	-
0.5378	12500	3.3447	-	-	-	-	-
0.5421	12600	3.6315	-	-	-	-	-
0.5464	12700	3.8674	-	-	-	-	-
0.5507	12800	3.4066	-	-	-	-	-
0.5550	12900	3.7356	-	-	-	-	-
0.5593	13000	3.5742	-	-	-	-	-
0.5636	13100	3.7676	-	-	-	-	-
0.5679	13200	3.7907	-	-	-	-	-
0.5722	13300	3.8089	-	-	-	-	-
0.5765	13400	3.4742	-	-	-	-	-
0.5808	13500	3.6536	-	-	-	-	-
0.5851	13600	3.7736	-	-	-	-	-
0.5894	13700	3.9072	-	-	-	-	-
0.5937	13800	3.7386	-	-	-	-	-
0.5980	13900	3.3387	-	-	-	-	-
0.6023	14000	3.5509	-	-	-	-	-
0.6066	14100	3.7056	-	-	-	-	-
0.6109	14200	3.7283	-	-	-	-	-
0.6152	14300	3.7301	-	-	-	-	-
0.6195	14400	3.8027	-	-	-	-	-
0.6238	14500	3.5606	-	-	-	-	-
0.6281	14600	3.9467	-	-	-	-	-
0.6324	14700	3.3394	-	-	-	-	-
0.6367	14800	4.1254	-	-	-	-	-
0.6410	14900	3.7121	-	-	-	-	-
0.6453	15000	3.9167	-	-	-	-	-
0.6496	15100	3.8084	-	-	-	-	-
0.6539	15200	3.7794	-	-	-	-	-
0.6582	15300	3.7664	-	-	-	-	-
0.6625	15400	3.4378	-	-	-	-	-
0.6668	15500	3.6632	-	-	-	-	-
0.6711	15600	3.8493	-	-	-	-	-
0.6754	15700	4.1475	-	-	-	-	-
0.6797	15800	3.5782	-	-	-	-	-
0.6840	15900	3.4341	-	-	-	-	-
0.6883	16000	3.3295	-	-	-	-	-
0.6927	16100	3.8165	-	-	-	-	-
0.6970	16200	3.9702	-	-	-	-	-
0.7013	16300	3.6555	-	-	-	-	-
0.7056	16400	3.6946	-	-	-	-	-
0.7099	16500	3.8027	-	-	-	-	-
0.7142	16600	3.4523	-	-	-	-	-
0.7185	16700	3.461	-	-	-	-	-
0.7228	16800	3.4403	-	-	-	-	-
0.7271	16900	3.6398	-	-	-	-	-
0.7314	17000	3.8443	-	-	-	-	-
0.7357	17100	3.6012	-	-	-	-	-
0.7400	17200	3.6645	-	-	-	-	-
0.7443	17300	3.4899	-	-	-	-	-
0.7486	17400	3.7186	-	-	-	-	-
0.7529	17500	3.6199	-	-	-	-	-
0.7572	17600	4.4274	-	-	-	-	-
0.7615	17700	4.0262	-	-	-	-	-
0.7658	17800	3.9325	-	-	-	-	-
0.7701	17900	3.6338	-	-	-	-	-
0.7744	18000	3.6136	-	-	-	-	-
0.7787	18100	3.4514	-	-	-	-	-
0.7830	18200	3.4427	-	-	-	-	-
0.7873	18300	3.3601	-	-	-	-	-
0.7916	18400	3.313	-	-	-	-	-
0.7959	18500	3.4062	-	-	-	-	-
0.8002	18600	3.098	-	-	-	-	-
0.8045	18700	3.183	-	-	-	-	-
0.8088	18800	3.1482	-	-	-	-	-
0.8131	18900	3.0122	-	-	-	-	-
0.8174	19000	3.0828	-	-	-	-	-
0.8217	19100	3.063	-	-	-	-	-
0.8260	19200	2.9688	-	-	-	-	-
0.8303	19300	3.0425	-	-	-	-	-
0.8346	19400	3.2018	-	-	-	-	-
0.8389	19500	2.9111	-	-	-	-	-
0.8432	19600	2.9516	-	-	-	-	-
0.8475	19700	2.9115	-	-	-	-	-
0.8518	19800	2.9323	-	-	-	-	-
0.8561	19900	2.8753	-	-	-	-	-
0.8604	20000	2.8344	-	-	-	-	-
0.8647	20100	2.7665	-	-	-	-	-
0.8690	20200	2.7732	-	-	-	-	-
0.8733	20300	2.8622	-	-	-	-	-
0.8776	20400	2.8749	-	-	-	-	-
0.8819	20500	2.8534	-	-	-	-	-
0.8863	20600	2.9254	-	-	-	-	-
0.8906	20700	2.7366	-	-	-	-	-
0.8949	20800	2.7287	-	-	-	-	-
0.8992	20900	2.9469	-	-	-	-	-
0.9035	21000	2.9052	-	-	-	-	-
0.9078	21100	2.7256	-	-	-	-	-
0.9121	21200	2.8469	-	-	-	-	-
0.9164	21300	2.6626	-	-	-	-	-
0.9207	21400	2.6796	-	-	-	-	-
0.9250	21500	2.6927	-	-	-	-	-
0.9293	21600	2.7125	-	-	-	-	-
0.9336	21700	2.6734	-	-	-	-	-
0.9379	21800	2.7199	-	-	-	-	-
0.9422	21900	2.6635	-	-	-	-	-
0.9465	22000	2.5218	-	-	-	-	-
0.9508	22100	2.7595	-	-	-	-	-
0.9551	22200	2.6821	-	-	-	-	-
0.9594	22300	2.6578	-	-	-	-	-
0.9637	22400	2.568	-	-	-	-	-
0.9680	22500	2.5527	-	-	-	-	-
0.9723	22600	2.6857	-	-	-	-	-
0.9766	22700	2.6637	-	-	-	-	-
0.9809	22800	2.6311	-	-	-	-	-
0.9852	22900	2.4635	-	-	-	-	-
0.9895	23000	2.6239	-	-	-	-	-
0.9938	23100	2.6873	-	-	-	-	-
0.9981	23200	2.5138	-	-	-	-	-
1.0	23244	-	0.6670	0.6815	0.6859	0.6524	0.6872

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}
}