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: Geotrend/bert-base-sw-cased
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 Geotrend/bert-base-sw-cased
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.6937245827269046
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6872564222432196
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6671541268726737
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6578428252987948
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6672292642346008
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6577692881532263
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5234944445417878
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5126395384896926
            name: Spearman Dot
          - type: pearson_max
            value: 0.6937245827269046
            name: Pearson Max
          - type: spearman_max
            value: 0.6872564222432196
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.689885399601221
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6847071916895495
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6678379220949281
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6579957115799916
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6673062843667007
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6573006123381013
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.49533316366864977
            name: Pearson Dot
          - type: spearman_dot
            value: 0.48723679408818543
            name: Spearman Dot
          - type: pearson_max
            value: 0.689885399601221
            name: Pearson Max
          - type: spearman_max
            value: 0.6847071916895495
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.6873377612773459
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6816874105466478
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.667357515297651
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6557727891191705
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6674937201647584
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6560441259953166
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.45660372834373963
            name: Pearson Dot
          - type: spearman_dot
            value: 0.4533070407260065
            name: Spearman Dot
          - type: pearson_max
            value: 0.6873377612773459
            name: Pearson Max
          - type: spearman_max
            value: 0.6816874105466478
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.6836009506667413
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6795423695973911
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6663652896396122
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6534731725514219
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6663726876345561
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6537216014002204
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.43102957451470686
            name: Pearson Dot
          - type: spearman_dot
            value: 0.431538008932168
            name: Spearman Dot
          - type: pearson_max
            value: 0.6836009506667413
            name: Pearson Max
          - type: spearman_max
            value: 0.6795423695973911
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.6715253560367674
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.669070001537953
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6571390159051358
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6456119247619697
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6598587843081631
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6472279949159918
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.36757468941627225
            name: Pearson Dot
          - type: spearman_dot
            value: 0.3678274698380672
            name: Spearman Dot
          - type: pearson_max
            value: 0.6715253560367674
            name: Pearson Max
          - type: spearman_max
            value: 0.669070001537953
            name: Spearman Max

SentenceTransformer based on Geotrend/bert-base-sw-cased

This is a sentence-transformers model finetuned from Geotrend/bert-base-sw-cased 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: Geotrend/bert-base-sw-cased
Maximum Sequence Length: 512 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': 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("sartifyllc/MultiLinguSwahili-bert-base-sw-cased-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	0.6937
spearman_cosine	0.6873
pearson_manhattan	0.6672
spearman_manhattan	0.6578
pearson_euclidean	0.6672
spearman_euclidean	0.6578
pearson_dot	0.5235
spearman_dot	0.5126
pearson_max	0.6937
spearman_max	0.6873

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6899
spearman_cosine	0.6847
pearson_manhattan	0.6678
spearman_manhattan	0.658
pearson_euclidean	0.6673
spearman_euclidean	0.6573
pearson_dot	0.4953
spearman_dot	0.4872
pearson_max	0.6899
spearman_max	0.6847

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6873
spearman_cosine	0.6817
pearson_manhattan	0.6674
spearman_manhattan	0.6558
pearson_euclidean	0.6675
spearman_euclidean	0.656
pearson_dot	0.4566
spearman_dot	0.4533
pearson_max	0.6873
spearman_max	0.6817

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6836
spearman_cosine	0.6795
pearson_manhattan	0.6664
spearman_manhattan	0.6535
pearson_euclidean	0.6664
spearman_euclidean	0.6537
pearson_dot	0.431
spearman_dot	0.4315
pearson_max	0.6836
spearman_max	0.6795

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6715
spearman_cosine	0.6691
pearson_manhattan	0.6571
spearman_manhattan	0.6456
pearson_euclidean	0.6599
spearman_euclidean	0.6472
pearson_dot	0.3676
spearman_dot	0.3678
pearson_max	0.6715
spearman_max	0.6691

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: 9 tokens mean: 16.73 tokens max: 71 tokens	min: 6 tokens mean: 19.74 tokens max: 45 tokens	min: 6 tokens mean: 19.0 tokens max: 49 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: 7 tokens mean: 28.25 tokens max: 82 tokens	min: 5 tokens mean: 14.16 tokens max: 55 tokens	min: 5 tokens mean: 15.55 tokens max: 46 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: 32
per_device_eval_batch_size: 32
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: 32
per_device_eval_batch_size: 32
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
0.0057	100	19.9104	-	-	-	-	-
0.0115	200	15.4038	-	-	-	-	-
0.0172	300	12.4565	-	-	-	-	-
0.0229	400	11.8633	-	-	-	-	-
0.0287	500	11.0601	-	-	-	-	-
0.0344	600	9.7725	-	-	-	-	-
0.0402	700	8.8549	-	-	-	-	-
0.0459	800	8.0831	-	-	-	-	-
0.0516	900	7.9941	-	-	-	-	-
0.0574	1000	7.6537	-	-	-	-	-
0.0631	1100	7.9303	-	-	-	-	-
0.0688	1200	7.5246	-	-	-	-	-
0.0746	1300	7.7754	-	-	-	-	-
0.0803	1400	7.668	-	-	-	-	-
0.0860	1500	6.7171	-	-	-	-	-
0.0918	1600	6.347	-	-	-	-	-
0.0975	1700	6.0	-	-	-	-	-
0.1033	1800	6.4314	-	-	-	-	-
0.1090	1900	6.7947	-	-	-	-	-
0.1147	2000	6.9316	-	-	-	-	-
0.1205	2100	6.6304	-	-	-	-	-
0.1262	2200	6.132	-	-	-	-	-
0.1319	2300	5.8953	-	-	-	-	-
0.1377	2400	5.6954	-	-	-	-	-
0.1434	2500	5.6832	-	-	-	-	-
0.1491	2600	5.2266	-	-	-	-	-
0.1549	2700	5.0678	-	-	-	-	-
0.1606	2800	5.4733	-	-	-	-	-
0.1664	2900	6.0899	-	-	-	-	-
0.1721	3000	6.332	-	-	-	-	-
0.1778	3100	6.4937	-	-	-	-	-
0.1836	3200	6.2242	-	-	-	-	-
0.1893	3300	5.8023	-	-	-	-	-
0.1950	3400	5.0745	-	-	-	-	-
0.2008	3500	5.5806	-	-	-	-	-
0.2065	3600	5.5191	-	-	-	-	-
0.2122	3700	5.3849	-	-	-	-	-
0.2180	3800	5.4828	-	-	-	-	-
0.2237	3900	5.9982	-	-	-	-	-
0.2294	4000	5.6842	-	-	-	-	-
0.2352	4100	5.1627	-	-	-	-	-
0.2409	4200	5.154	-	-	-	-	-
0.2467	4300	5.7932	-	-	-	-	-
0.2524	4400	5.5758	-	-	-	-	-
0.2581	4500	5.5212	-	-	-	-	-
0.2639	4600	5.5692	-	-	-	-	-
0.2696	4700	5.2699	-	-	-	-	-
0.2753	4800	5.4919	-	-	-	-	-
0.2811	4900	5.0754	-	-	-	-	-
0.2868	5000	5.1514	-	-	-	-	-
0.2925	5100	5.0241	-	-	-	-	-
0.2983	5200	5.2679	-	-	-	-	-
0.3040	5300	5.3576	-	-	-	-	-
0.3098	5400	5.3454	-	-	-	-	-
0.3155	5500	5.2142	-	-	-	-	-
0.3212	5600	4.8418	-	-	-	-	-
0.3270	5700	4.9597	-	-	-	-	-
0.3327	5800	5.1989	-	-	-	-	-
0.3384	5900	5.2624	-	-	-	-	-
0.3442	6000	5.0705	-	-	-	-	-
0.3499	6100	5.232	-	-	-	-	-
0.3556	6200	5.2428	-	-	-	-	-
0.3614	6300	4.755	-	-	-	-	-
0.3671	6400	4.7266	-	-	-	-	-
0.3729	6500	4.6452	-	-	-	-	-
0.3786	6600	5.1431	-	-	-	-	-
0.3843	6700	4.5343	-	-	-	-	-
0.3901	6800	4.698	-	-	-	-	-
0.3958	6900	4.6944	-	-	-	-	-
0.4015	7000	4.6255	-	-	-	-	-
0.4073	7100	5.0211	-	-	-	-	-
0.4130	7200	4.6974	-	-	-	-	-
0.4187	7300	4.9182	-	-	-	-	-
0.4245	7400	4.652	-	-	-	-	-
0.4302	7500	5.1015	-	-	-	-	-
0.4360	7600	4.5249	-	-	-	-	-
0.4417	7700	4.455	-	-	-	-	-
0.4474	7800	4.8153	-	-	-	-	-
0.4532	7900	4.7665	-	-	-	-	-
0.4589	8000	4.3413	-	-	-	-	-
0.4646	8100	4.4697	-	-	-	-	-
0.4704	8200	4.6776	-	-	-	-	-
0.4761	8300	4.2868	-	-	-	-	-
0.4818	8400	4.7052	-	-	-	-	-
0.4876	8500	4.4721	-	-	-	-	-
0.4933	8600	4.6926	-	-	-	-	-
0.4991	8700	4.9891	-	-	-	-	-
0.5048	8800	4.4837	-	-	-	-	-
0.5105	8900	4.8127	-	-	-	-	-
0.5163	9000	4.3438	-	-	-	-	-
0.5220	9100	4.4743	-	-	-	-	-
0.5277	9200	4.6879	-	-	-	-	-
0.5335	9300	4.3593	-	-	-	-	-
0.5392	9400	4.3023	-	-	-	-	-
0.5449	9500	4.8188	-	-	-	-	-
0.5507	9600	4.6142	-	-	-	-	-
0.5564	9700	4.7679	-	-	-	-	-
0.5622	9800	4.6224	-	-	-	-	-
0.5679	9900	4.9154	-	-	-	-	-
0.5736	10000	4.7557	-	-	-	-	-
0.5794	10100	4.6395	-	-	-	-	-
0.5851	10200	4.7977	-	-	-	-	-
0.5908	10300	4.915	-	-	-	-	-
0.5966	10400	4.4854	-	-	-	-	-
0.6023	10500	4.3973	-	-	-	-	-
0.6080	10600	4.6964	-	-	-	-	-
0.6138	10700	4.8853	-	-	-	-	-
0.6195	10800	4.786	-	-	-	-	-
0.6253	10900	4.5482	-	-	-	-	-
0.6310	11000	4.4857	-	-	-	-	-
0.6367	11100	4.7415	-	-	-	-	-
0.6425	11200	4.2596	-	-	-	-	-
0.6482	11300	4.8578	-	-	-	-	-
0.6539	11400	4.5471	-	-	-	-	-
0.6597	11500	4.8337	-	-	-	-	-
0.6654	11600	4.2244	-	-	-	-	-
0.6711	11700	4.9619	-	-	-	-	-
0.6769	11800	4.9369	-	-	-	-	-
0.6826	11900	4.2697	-	-	-	-	-
0.6883	12000	4.2711	-	-	-	-	-
0.6941	12100	4.6396	-	-	-	-	-
0.6998	12200	4.5626	-	-	-	-	-
0.7056	12300	4.5767	-	-	-	-	-
0.7113	12400	4.6449	-	-	-	-	-
0.7170	12500	4.4217	-	-	-	-	-
0.7228	12600	4.0203	-	-	-	-	-
0.7285	12700	4.5381	-	-	-	-	-
0.7342	12800	4.5865	-	-	-	-	-
0.7400	12900	4.4203	-	-	-	-	-
0.7457	13000	4.3761	-	-	-	-	-
0.7514	13100	4.093	-	-	-	-	-
0.7572	13200	5.9235	-	-	-	-	-
0.7629	13300	5.4098	-	-	-	-	-
0.7687	13400	5.3079	-	-	-	-	-
0.7744	13500	5.0946	-	-	-	-	-
0.7801	13600	4.7098	-	-	-	-	-
0.7859	13700	4.9471	-	-	-	-	-
0.7916	13800	4.5742	-	-	-	-	-
0.7973	13900	4.6178	-	-	-	-	-
0.8031	14000	4.4516	-	-	-	-	-
0.8088	14100	4.429	-	-	-	-	-
0.8145	14200	4.3812	-	-	-	-	-
0.8203	14300	4.3739	-	-	-	-	-
0.8260	14400	4.3821	-	-	-	-	-
0.8318	14500	4.4396	-	-	-	-	-
0.8375	14600	4.2667	-	-	-	-	-
0.8432	14700	4.1963	-	-	-	-	-
0.8490	14800	4.1298	-	-	-	-	-
0.8547	14900	4.1843	-	-	-	-	-
0.8604	15000	4.0735	-	-	-	-	-
0.8662	15100	3.9319	-	-	-	-	-
0.8719	15200	4.1544	-	-	-	-	-
0.8776	15300	4.105	-	-	-	-	-
0.8834	15400	4.014	-	-	-	-	-
0.8891	15500	4.0345	-	-	-	-	-
0.8949	15600	3.9127	-	-	-	-	-
0.9006	15700	4.1002	-	-	-	-	-
0.9063	15800	3.8564	-	-	-	-	-
0.9121	15900	3.9297	-	-	-	-	-
0.9178	16000	3.8487	-	-	-	-	-
0.9235	16100	3.7099	-	-	-	-	-
0.9293	16200	3.8545	-	-	-	-	-
0.9350	16300	3.8122	-	-	-	-	-
0.9407	16400	3.8951	-	-	-	-	-
0.9465	16500	3.6996	-	-	-	-	-
0.9522	16600	3.9081	-	-	-	-	-
0.9580	16700	3.8603	-	-	-	-	-
0.9637	16800	3.8534	-	-	-	-	-
0.9694	16900	3.8145	-	-	-	-	-
0.9752	17000	3.9858	-	-	-	-	-
0.9809	17100	3.8224	-	-	-	-	-
0.9866	17200	3.7469	-	-	-	-	-
0.9924	17300	3.9066	-	-	-	-	-
0.9981	17400	3.6754	-	-	-	-	-
1.0	17433	-	0.6795	0.6817	0.6847	0.6691	0.6873

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}
}