README.md

metadata

language:
  - es
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:14907
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: jinaai/jina-embeddings-v3
widget:
  - source_sentence: >-
      Describe la tradición del 'rosario de candiles' en el contexto de la
      minería.
    sentences:
      - >-
        Un mechazo es la combustión de la mecha sin que se llegue a inflamar el
        barreno.
      - >-
        La siega tradicional en Escucha comenzaba antes de San Juan con las
        cebadas.
      - >-
        El 'rosario de candiles' es una tradición religiosa celebrada en la
        festividad de San Juan, en la que los mineros escuchan y acompañan con
        sus candiles de carburo, rezando a dos coros y cantando en parte.
  - source_sentence: ¿Qué significa la expresión 'pillar una mojadina'?
    sentences:
      - >-
        En el campeonato provincial de atletismo en Alcorisa en mayo, Pilar
        Brumos de Escucha logró la 3ª posición en 600 metros y el subcampeonato
        en peso.
      - >-
        Los empresarios de Escucha se habían unido para poder participar en las
        elecciones a CC.PP. ya que era necesario que la plantilla de la empresa
        superase el número de 50 trabajadores..
      - '''Pillar una mojadina'' significa empaparse, quedar empapado.'
  - source_sentence: ¿En qué año Carbones de Teruel registra la mina 'pablo' en Escucha?
    sentences:
      - Puede referirse a un calcetín para bebés o a un calcetín gordo.
      - Carbones de Teruel registra la mina 'pablo' en Escucha en 1900.
      - >-
        Jesús Conesa explicó a la Junta de Espectáculos que el anterior
        propietario, Sr. Latorre Galindo, tenía otro cine en Utrillas, lo que
        causaba continuos equívocos en envíos de material y pagos, al creerse
        que ambos cines le pertenecían o eran la misma empresa. 
  - source_sentence: ¿Quién regentaba el Cine Avenida de Escucha en el momento de su cierre?
    sentences:
      - Se usa con el significado de 'cuando'.
      - >-
        El CD Escucha alineó a Castillo, Romero, Bobadilla, Moraleda, Luis,
        González, Higinio, Torres, Calomarde I, Calomarde II y Navarro en el
        partido de Copa contra el Alcorisa.
      - >-
        Antonio Malpica regentaba el Cine Avenida de Escucha en el momento de su
        cierre.
  - source_sentence: >-
      ¿Qué porcentaje de aumento salarial reclamaba el Sindicato Minero en el
      conflicto de Utrillas que llevó a plantear la huelga del 12 de octubre de
      1930?
    sentences:
      - Antonio Gargallo.
      - >-
        Una publicación con una fotografía para el recuerdo de la locomotora
        llamada 'Escucha'.
      - >-
        El Sindicato Minero reclamaba un aumento del 20% los sueldos en el
        conflicto de Utrillas.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: Lampistero
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 1024
          type: dim_1024
        metrics:
          - type: cosine_accuracy@1
            value: 0.7803258901629451
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8883524441762221
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.904043452021726
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9233554616777309
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7803258901629451
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29611748139207406
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18080869040434522
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09233554616777308
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7803258901629451
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8883524441762221
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.904043452021726
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9233554616777309
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8576141434466037
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8359425142014155
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8374344979701236
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.7827398913699457
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8877489438744719
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9034399517199758
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9245624622812312
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7827398913699457
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.295916314624824
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18068799034399516
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09245624622812311
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7827398913699457
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8877489438744719
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9034399517199758
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9245624622812312
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.858770916125463
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8371705894186279
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8385437636605255
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.7797223898611949
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8859384429692215
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9010259505129753
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9227519613759807
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7797223898611949
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2953128143230738
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18020519010259503
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09227519613759806
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7797223898611949
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8859384429692215
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9010259505129753
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9227519613759807
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8564496755344808
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8346785163471941
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8361853082918266
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.7706698853349426
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8823174411587206
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9016294508147255
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9191309595654797
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7706698853349426
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2941058137195735
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18032589016294506
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09191309595654798
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7706698853349426
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8823174411587206
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9016294508147255
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9191309595654797
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.851155539622205
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8286940445057519
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8302805177061129
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.7604103802051901
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8690404345202173
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8901629450814725
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9130959565479783
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7604103802051901
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28968014484007243
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1780325890162945
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09130959565479783
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7604103802051901
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8690404345202173
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8901629450814725
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9130959565479783
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8415141158022221
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8181217729497756
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8199539602494803
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.7248038624019312
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.852142426071213
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8750754375377188
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8974049487024743
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7248038624019312
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28404747535707103
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17501508750754374
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08974049487024743
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7248038624019312
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.852142426071213
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8750754375377188
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8974049487024743
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8181789750224895
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7920167926353802
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.793825252598125
            name: Cosine Map@100

Lampistero

This is a sentence-transformers model finetuned from jinaai/jina-embeddings-v3 on the json 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: jinaai/jina-embeddings-v3
• Maximum Sequence Length: 8194 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json
• Language: es
• License: apache-2.0

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (transformer): Transformer(
    (auto_model): XLMRobertaLoRA(
      (roberta): XLMRobertaModel(
        (embeddings): XLMRobertaEmbeddings(
          (word_embeddings): ParametrizedEmbedding(
            250002, 1024, padding_idx=1
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
          (token_type_embeddings): ParametrizedEmbedding(
            1, 1024
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
        )
        (emb_drop): Dropout(p=0.1, inplace=False)
        (emb_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        (encoder): XLMRobertaEncoder(
          (layers): ModuleList(
            (0-23): 24 x Block(
              (mixer): MHA(
                (rotary_emb): RotaryEmbedding()
                (Wqkv): ParametrizedLinearResidual(
                  in_features=1024, out_features=3072, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
                (inner_attn): FlashSelfAttention(
                  (drop): Dropout(p=0.1, inplace=False)
                )
                (inner_cross_attn): FlashCrossAttention(
                  (drop): Dropout(p=0.1, inplace=False)
                )
                (out_proj): ParametrizedLinear(
                  in_features=1024, out_features=1024, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
              )
              (dropout1): Dropout(p=0.1, inplace=False)
              (drop_path1): StochasticDepth(p=0.0, mode=row)
              (norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              (mlp): Mlp(
                (fc1): ParametrizedLinear(
                  in_features=1024, out_features=4096, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
                (fc2): ParametrizedLinear(
                  in_features=4096, out_features=1024, bias=True
                  (parametrizations): ModuleDict(
                    (weight): ParametrizationList(
                      (0): LoRAParametrization()
                    )
                  )
                )
              )
              (dropout2): Dropout(p=0.1, inplace=False)
              (drop_path2): StochasticDepth(p=0.0, mode=row)
              (norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            )
          )
        )
        (pooler): XLMRobertaPooler(
          (dense): ParametrizedLinear(
            in_features=1024, out_features=1024, bias=True
            (parametrizations): ModuleDict(
              (weight): ParametrizationList(
                (0): LoRAParametrization()
              )
            )
          )
          (activation): Tanh()
        )
      )
    )
  )
  (pooler): Pooling({'word_embedding_dimension': 1024, '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})
  (normalizer): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("csanz91/lampistero_rag_embeddings")
# Run inference
sentences = [
    '¿Qué porcentaje de aumento salarial reclamaba el Sindicato Minero en el conflicto de Utrillas que llevó a plantear la huelga del 12 de octubre de 1930?',
    'El Sindicato Minero reclamaba un aumento del 20% los sueldos en el conflicto de Utrillas.',
    'Antonio Gargallo.',
]
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

Information Retrieval

• Dataset: dim_1024
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 1024
  }
  

Metric	Value
cosine_accuracy@1	0.7803
cosine_accuracy@3	0.8884
cosine_accuracy@5	0.904
cosine_accuracy@10	0.9234
cosine_precision@1	0.7803
cosine_precision@3	0.2961
cosine_precision@5	0.1808
cosine_precision@10	0.0923
cosine_recall@1	0.7803
cosine_recall@3	0.8884
cosine_recall@5	0.904
cosine_recall@10	0.9234
cosine_ndcg@10	0.8576
cosine_mrr@10	0.8359
cosine_map@100	0.8374

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 768
  }
  

Metric	Value
cosine_accuracy@1	0.7827
cosine_accuracy@3	0.8877
cosine_accuracy@5	0.9034
cosine_accuracy@10	0.9246
cosine_precision@1	0.7827
cosine_precision@3	0.2959
cosine_precision@5	0.1807
cosine_precision@10	0.0925
cosine_recall@1	0.7827
cosine_recall@3	0.8877
cosine_recall@5	0.9034
cosine_recall@10	0.9246
cosine_ndcg@10	0.8588
cosine_mrr@10	0.8372
cosine_map@100	0.8385

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 512
  }
  

Metric	Value
cosine_accuracy@1	0.7797
cosine_accuracy@3	0.8859
cosine_accuracy@5	0.901
cosine_accuracy@10	0.9228
cosine_precision@1	0.7797
cosine_precision@3	0.2953
cosine_precision@5	0.1802
cosine_precision@10	0.0923
cosine_recall@1	0.7797
cosine_recall@3	0.8859
cosine_recall@5	0.901
cosine_recall@10	0.9228
cosine_ndcg@10	0.8564
cosine_mrr@10	0.8347
cosine_map@100	0.8362

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 256
  }
  

Metric	Value
cosine_accuracy@1	0.7707
cosine_accuracy@3	0.8823
cosine_accuracy@5	0.9016
cosine_accuracy@10	0.9191
cosine_precision@1	0.7707
cosine_precision@3	0.2941
cosine_precision@5	0.1803
cosine_precision@10	0.0919
cosine_recall@1	0.7707
cosine_recall@3	0.8823
cosine_recall@5	0.9016
cosine_recall@10	0.9191
cosine_ndcg@10	0.8512
cosine_mrr@10	0.8287
cosine_map@100	0.8303

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 128
  }
  

Metric	Value
cosine_accuracy@1	0.7604
cosine_accuracy@3	0.869
cosine_accuracy@5	0.8902
cosine_accuracy@10	0.9131
cosine_precision@1	0.7604
cosine_precision@3	0.2897
cosine_precision@5	0.178
cosine_precision@10	0.0913
cosine_recall@1	0.7604
cosine_recall@3	0.869
cosine_recall@5	0.8902
cosine_recall@10	0.9131
cosine_ndcg@10	0.8415
cosine_mrr@10	0.8181
cosine_map@100	0.82

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 64
  }
  

Metric	Value
cosine_accuracy@1	0.7248
cosine_accuracy@3	0.8521
cosine_accuracy@5	0.8751
cosine_accuracy@10	0.8974
cosine_precision@1	0.7248
cosine_precision@3	0.284
cosine_precision@5	0.175
cosine_precision@10	0.0897
cosine_recall@1	0.7248
cosine_recall@3	0.8521
cosine_recall@5	0.8751
cosine_recall@10	0.8974
cosine_ndcg@10	0.8182
cosine_mrr@10	0.792
cosine_map@100	0.7938

Training Details

Training Dataset

json

• Dataset: json
• Size: 14,907 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 9 tokens mean: 25.88 tokens max: 63 tokens	min: 3 tokens mean: 34.09 tokens max: 340 tokens

• Samples:

  query	answer
  En Valdeconejos, ¿cuál era la sociedad de agricultores en 1952?	En Valdeconejos, la sociedad de agricultores en 1952 era el Pósito de Agricultores.
  ¿Qué nombres de capataces se registran en el pueblo de Escucha en el año 1952?	En Escucha, en 1952, los capataces registrados son Peralta (Manuel) y Rodriguez (Gonzalo).
  En el contexto de la minería, ¿qué implica 'despajar'?	'Despajar' se refiere a cribar a mano material y desechos para obtener las partes de carbón que hay en ellos.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "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: epoch
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 32
• learning_rate: 2e-05
• num_train_epochs: 12
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• tf32: True
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 32
• eval_accumulation_steps: None
• torch_empty_cache_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: 12
• max_steps: -1
• lr_scheduler_type: cosine
• 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: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: True
• 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: True
• 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}
• tp_size: 0
• 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_fused
• 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: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_1024_cosine_ndcg@10	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	8	-	0.7663	0.7676	0.7656	0.7626	0.7393	0.6969
1.2747	10	127.0406	-	-	-	-	-	-
2.0	16	-	0.8244	0.8240	0.8226	0.8172	0.8060	0.7775
2.5494	20	38.8995	-	-	-	-	-	-
3.0	24	-	0.8425	0.8426	0.8444	0.8373	0.8252	0.7996
3.8240	30	20.1528	-	-	-	-	-	-
4.0	32	-	0.8526	0.8520	0.8498	0.8456	0.8289	0.8037
5.0	40	14.0513	0.8550	0.8543	0.8517	0.8490	0.8368	0.8139
6.0	48	-	0.8572	0.8565	0.8557	0.8520	0.8404	0.8170
6.2747	50	13.364	-	-	-	-	-	-
7.0	56	-	0.8579	0.8576	0.8553	0.8514	0.8422	0.8180
7.5494	60	12.7986	-	-	-	-	-	-
8.0	64	-	0.8573	0.8580	0.8560	0.8523	0.8414	0.8178
8.8240	70	12.0091	-	-	-	-	-	-
9.0	72	-	0.8578	0.8586	0.8562	0.8519	0.8423	0.8184
10.0	80	10.9468	0.8583	0.8589	0.8565	0.8530	0.8413	0.8191
10.5494	84	-	0.8576	0.8588	0.8564	0.8512	0.8415	0.8182

Framework Versions

• Python: 3.12.10
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.7.0+cu126
• Accelerate: 1.7.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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}
}