metadata

language:
  - de
  - en
  - es
  - fr
  - it
  - nl
  - pl
  - pt
  - ru
  - zh
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:10K<n<100K
  - loss:MatryoshkaLoss
  - loss:CosineSimilarityLoss
base_model: aari1995/gbert-large-2-cls-nlisim
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: Ein Mann spricht.
    sentences:
      - Ein Mann spricht in ein Mikrofon.
      - Der Mann spielt auf den Tastaturen.
      - Zwei Mädchen gehen im Ozean spazieren.
  - source_sentence: Eine Flagge weht.
    sentences:
      - Die Flagge bewegte sich in der Luft.
      - Ein Hund fährt auf einem Skateboard.
      - Zwei Frauen sitzen in einem Cafe.
  - source_sentence: Ein Mann übt Boxen
    sentences:
      - Ein Affe praktiziert Kampfsportarten.
      - Eine Person faltet ein Blatt Papier.
      - Eine Frau geht mit ihrem Hund spazieren.
  - source_sentence: Das Tor ist gelb.
    sentences:
      - Das Tor ist blau.
      - Die Frau hält die Hände des Mannes.
      - NATO-Soldat bei afghanischem Angriff getötet
  - source_sentence: Zwei Frauen laufen.
    sentences:
      - Frauen laufen.
      - Die Frau prüft die Augen des Mannes.
      - Ein Mann ist auf einem Dach
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on aari1995/gbert-large-2-cls-nlisim
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 1024
          type: sts-dev-1024
        metrics:
          - type: pearson_cosine
            value: 0.8417806877288009
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8452891310343582
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8418749526406495
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8450348906331776
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8422615095001257
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8453390990427703
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8416625079549063
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8450616171323844
            name: Spearman Dot
          - type: pearson_max
            value: 0.8422615095001257
            name: Pearson Max
          - type: spearman_max
            value: 0.8453390990427703
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 768
          type: sts-dev-768
        metrics:
          - type: pearson_cosine
            value: 0.8418107096367227
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8453863409322975
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8418527770289471
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8448328869253576
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8422791953749277
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8451547857394669
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8417682812591724
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8446927200809794
            name: Spearman Dot
          - type: pearson_max
            value: 0.8422791953749277
            name: Pearson Max
          - type: spearman_max
            value: 0.8453863409322975
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 512
          type: sts-dev-512
        metrics:
          - type: pearson_cosine
            value: 0.8394808864309438
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8437551103291275
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8420246416513741
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8447335398769396
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8422722079216611
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8448909261141044
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8358204287638725
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8380004733308642
            name: Spearman Dot
          - type: pearson_max
            value: 0.8422722079216611
            name: Pearson Max
          - type: spearman_max
            value: 0.8448909261141044
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 256
          type: sts-dev-256
        metrics:
          - type: pearson_cosine
            value: 0.833879413726309
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8392439788855341
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8379618268497928
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.839860826315925
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.838931461279174
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8404811150299943
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8230557648139373
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8242532718299653
            name: Spearman Dot
          - type: pearson_max
            value: 0.838931461279174
            name: Pearson Max
          - type: spearman_max
            value: 0.8404811150299943
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 128
          type: sts-dev-128
        metrics:
          - type: pearson_cosine
            value: 0.8253967606033702
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8335750690073012
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8341588626988476
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8343994326050966
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8355263623880292
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8358857095028451
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8035163216908426
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8050271037746011
            name: Spearman Dot
          - type: pearson_max
            value: 0.8355263623880292
            name: Pearson Max
          - type: spearman_max
            value: 0.8358857095028451
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 64
          type: sts-dev-64
        metrics:
          - type: pearson_cosine
            value: 0.8150661334039712
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8265558538619309
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8241988539394505
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8238763145175863
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8274925218859535
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8270778062044848
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7773847317840161
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7790338242936304
            name: Spearman Dot
          - type: pearson_max
            value: 0.8274925218859535
            name: Pearson Max
          - type: spearman_max
            value: 0.8270778062044848
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 1024
          type: sts-test-1024
        metrics:
          - type: pearson_cosine
            value: 0.8130772714952826
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8188901246173036
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8208715312691268
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8195095089412118
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.820344720619671
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8189263018901494
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8127924456922464
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8185815083131535
            name: Spearman Dot
          - type: pearson_max
            value: 0.8208715312691268
            name: Pearson Max
          - type: spearman_max
            value: 0.8195095089412118
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.8121757739236393
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8182913347635533
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.820604714791802
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8190481839997107
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8197462057663948
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8183157116237637
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8106698462984598
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8148932181769889
            name: Spearman Dot
          - type: pearson_max
            value: 0.820604714791802
            name: Pearson Max
          - type: spearman_max
            value: 0.8190481839997107
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.8096452235754106
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.816264314810491
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8180021560255247
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8165486306356095
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8173829404008947
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8158592878546184
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8059176831913651
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8088972406630007
            name: Spearman Dot
          - type: pearson_max
            value: 0.8180021560255247
            name: Pearson Max
          - type: spearman_max
            value: 0.8165486306356095
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.8070921035712145
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8150266310280979
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.818409081545237
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8167245415653657
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8176811220335696
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8158894222194816
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.795483328805793
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7956062163122977
            name: Spearman Dot
          - type: pearson_max
            value: 0.818409081545237
            name: Pearson Max
          - type: spearman_max
            value: 0.8167245415653657
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.7974039089035316
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8093067652791092
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8125792968401813
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8121486514324944
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8119102513178551
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.811152531425261
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7739555890021923
            name: Pearson Dot
          - type: spearman_dot
            value: 0.770072655568691
            name: Spearman Dot
          - type: pearson_max
            value: 0.8125792968401813
            name: Pearson Max
          - type: spearman_max
            value: 0.8121486514324944
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.7873069617689994
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8024994399645912
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8048161563115213
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8031972835914969
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8060416893207731
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8041515980374414
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.747911221220991
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7386011869481828
            name: Spearman Dot
          - type: pearson_max
            value: 0.8060416893207731
            name: Pearson Max
          - type: spearman_max
            value: 0.8041515980374414
            name: Spearman Max

SentenceTransformer based on aari1995/gbert-large-2-cls-nlisim

This is a sentence-transformers model finetuned from aari1995/gbert-large-2-cls-nlisim on the PhilipMay/stsb_multi_mt dataset. It maps sentences & paragraphs to a 1024-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: aari1995/gbert-large-2-cls-nlisim
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- PhilipMay/stsb_multi_mt
Languages: de, en, es, fr, it, nl, pl, pt, ru, zh

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: JinaBertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("aari1995/gbert-large-2-cls-pawsx-nli-sts")
# Run inference
sentences = [
    'Zwei Frauen laufen.',
    'Frauen laufen.',
    'Die Frau prüft die Augen des Mannes.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev-1024
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8418
spearman_cosine	0.8453
pearson_manhattan	0.8419
spearman_manhattan	0.845
pearson_euclidean	0.8423
spearman_euclidean	0.8453
pearson_dot	0.8417
spearman_dot	0.8451
pearson_max	0.8423
spearman_max	0.8453

Semantic Similarity

Dataset: sts-dev-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8418
spearman_cosine	0.8454
pearson_manhattan	0.8419
spearman_manhattan	0.8448
pearson_euclidean	0.8423
spearman_euclidean	0.8452
pearson_dot	0.8418
spearman_dot	0.8447
pearson_max	0.8423
spearman_max	0.8454

Semantic Similarity

Dataset: sts-dev-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8395
spearman_cosine	0.8438
pearson_manhattan	0.842
spearman_manhattan	0.8447
pearson_euclidean	0.8423
spearman_euclidean	0.8449
pearson_dot	0.8358
spearman_dot	0.838
pearson_max	0.8423
spearman_max	0.8449

Semantic Similarity

Dataset: sts-dev-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8339
spearman_cosine	0.8392
pearson_manhattan	0.838
spearman_manhattan	0.8399
pearson_euclidean	0.8389
spearman_euclidean	0.8405
pearson_dot	0.8231
spearman_dot	0.8243
pearson_max	0.8389
spearman_max	0.8405

Semantic Similarity

Dataset: sts-dev-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8254
spearman_cosine	0.8336
pearson_manhattan	0.8342
spearman_manhattan	0.8344
pearson_euclidean	0.8355
spearman_euclidean	0.8359
pearson_dot	0.8035
spearman_dot	0.805
pearson_max	0.8355
spearman_max	0.8359

Semantic Similarity

Dataset: sts-dev-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8151
spearman_cosine	0.8266
pearson_manhattan	0.8242
spearman_manhattan	0.8239
pearson_euclidean	0.8275
spearman_euclidean	0.8271
pearson_dot	0.7774
spearman_dot	0.779
pearson_max	0.8275
spearman_max	0.8271

Semantic Similarity

Dataset: sts-test-1024
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8131
spearman_cosine	0.8189
pearson_manhattan	0.8209
spearman_manhattan	0.8195
pearson_euclidean	0.8203
spearman_euclidean	0.8189
pearson_dot	0.8128
spearman_dot	0.8186
pearson_max	0.8209
spearman_max	0.8195

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8122
spearman_cosine	0.8183
pearson_manhattan	0.8206
spearman_manhattan	0.819
pearson_euclidean	0.8197
spearman_euclidean	0.8183
pearson_dot	0.8107
spearman_dot	0.8149
pearson_max	0.8206
spearman_max	0.819

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8096
spearman_cosine	0.8163
pearson_manhattan	0.818
spearman_manhattan	0.8165
pearson_euclidean	0.8174
spearman_euclidean	0.8159
pearson_dot	0.8059
spearman_dot	0.8089
pearson_max	0.818
spearman_max	0.8165

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8071
spearman_cosine	0.815
pearson_manhattan	0.8184
spearman_manhattan	0.8167
pearson_euclidean	0.8177
spearman_euclidean	0.8159
pearson_dot	0.7955
spearman_dot	0.7956
pearson_max	0.8184
spearman_max	0.8167

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7974
spearman_cosine	0.8093
pearson_manhattan	0.8126
spearman_manhattan	0.8121
pearson_euclidean	0.8119
spearman_euclidean	0.8112
pearson_dot	0.774
spearman_dot	0.7701
pearson_max	0.8126
spearman_max	0.8121

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7873
spearman_cosine	0.8025
pearson_manhattan	0.8048
spearman_manhattan	0.8032
pearson_euclidean	0.806
spearman_euclidean	0.8042
pearson_dot	0.7479
spearman_dot	0.7386
pearson_max	0.806
spearman_max	0.8042

Training Details

Training Dataset

PhilipMay/stsb_multi_mt

Dataset: PhilipMay/stsb_multi_mt at 3acaa3d
Size: 22,996 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 18.13 tokens
max: 65 tokens

min: 6 tokens
mean: 18.25 tokens
max: 90 tokens

min: 0.0
mean: 0.54
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 18.13 tokens max: 65 tokens	min: 6 tokens mean: 18.25 tokens max: 90 tokens	min: 0.0 mean: 0.54 max: 1.0

Samples:

sentence1	sentence2	score
`schütze wegen mordes an schwarzem us-jugendlichen angeklagt`	`gedanken zu den rassenbeziehungen unter einem schwarzen präsidenten`	`0.1599999964237213`
`fußballspieler kicken einen fußball in das tor.`	`Ein Fußballspieler schießt ein Tor.`	`0.7599999904632568`
`obama lockert abschiebungsregeln für junge einwanderer`	`usa lockert abschiebebestimmungen für jugendliche: napolitano`	`0.800000011920929`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CosineSimilarityLoss",
    "matryoshka_dims": [
        1024,
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

PhilipMay/stsb_multi_mt

Dataset: PhilipMay/stsb_multi_mt at 3acaa3d
Size: 1,500 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 16.54 tokens
max: 53 tokens

min: 5 tokens
mean: 16.53 tokens
max: 47 tokens

min: 0.0
mean: 0.47
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 16.54 tokens max: 53 tokens	min: 5 tokens mean: 16.53 tokens max: 47 tokens	min: 0.0 mean: 0.47 max: 1.0

Samples:

sentence1	sentence2	score
`Ein Mann mit einem Schutzhelm tanzt.`	`Ein Mann mit einem Schutzhelm tanzt.`	`1.0`
`Ein kleines Kind reitet auf einem Pferd.`	`Ein Kind reitet auf einem Pferd.`	`0.949999988079071`
`Ein Mann verfüttert eine Maus an eine Schlange.`	`Der Mann füttert die Schlange mit einer Maus.`	`1.0`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CosineSimilarityLoss",
    "matryoshka_dims": [
        1024,
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 4
per_device_eval_batch_size: 16
learning_rate: 5e-06
num_train_epochs: 1
warmup_ratio: 0.1
bf16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 4
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-06
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: 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, '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
eval_on_start: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	sts-dev-1024_spearman_cosine	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-1024_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
0.0174	100	0.2958	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0348	200	0.2914	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0522	300	0.2691	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0696	400	0.253	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0870	500	0.2458	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1044	600	0.2594	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1218	700	0.2339	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1392	800	0.2245	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1565	900	0.2122	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1739	1000	0.2369	0.2394	0.8402	0.8277	0.8352	0.8393	0.8164	0.8404	-	-	-	-	-	-
0.1913	1100	0.2308	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2087	1200	0.2292	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2261	1300	0.2232	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2435	1400	0.2001	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2609	1500	0.2139	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2783	1600	0.1906	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2957	1700	0.1895	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3131	1800	0.2011	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3305	1900	0.1723	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3479	2000	0.1886	0.2340	0.8448	0.8321	0.8385	0.8435	0.8233	0.8449	-	-	-	-	-	-
0.3653	2100	0.1719	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3827	2200	0.1879	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4001	2300	0.187	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4175	2400	0.1487	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4349	2500	0.1752	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4523	2600	0.1475	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4696	2700	0.1695	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4870	2800	0.1615	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5044	2900	0.1558	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5218	3000	0.1713	0.2357	0.8457	0.8344	0.8406	0.8447	0.8266	0.8461	-	-	-	-	-	-
0.5392	3100	0.1556	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5566	3200	0.1743	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5740	3300	0.1426	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5914	3400	0.1519	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6088	3500	0.1763	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6262	3600	0.1456	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6436	3700	0.1649	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6610	3800	0.1427	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6784	3900	0.1284	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6958	4000	0.1533	0.2344	0.8417	0.8291	0.8357	0.8402	0.8225	0.8421	-	-	-	-	-	-
0.7132	4100	0.1397	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7306	4200	0.1505	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7480	4300	0.1355	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7654	4400	0.1275	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7827	4500	0.1599	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8001	4600	0.1493	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8175	4700	0.1497	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8349	4800	0.1492	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8523	4900	0.1378	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8697	5000	0.1391	0.2362	0.8453	0.8336	0.8392	0.8438	0.8266	0.8454	-	-	-	-	-	-
0.8871	5100	0.1622	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9045	5200	0.1456	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9219	5300	0.1367	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9393	5400	0.1243	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9567	5500	0.1389	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9741	5600	0.1338	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9915	5700	0.1146	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0	5749	-	-	-	-	-	-	-	-	0.8189	0.8093	0.8150	0.8163	0.8025	0.8183

Framework Versions

Python: 3.9.16
Sentence Transformers: 3.0.0
Transformers: 4.42.0.dev0
PyTorch: 2.2.2+cu118
Accelerate: 0.31.0
Datasets: 2.19.1
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}
}