metadata

base_model: BAAI/bge-base-en-v1.5
language:
  - en
library_name: sentence-transformers
license: apache-2.0
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:1K<n<10K
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Herkules na rozstajach
    sentences:
      - jak zinterpretować wymowę obrazu Herkules na rozstajach?
      - w jakim celu nowożeńcom w Korei wręcza się injeolmi?
      - z jakiego powodu zwołano synod w Whitby?
  - source_sentence: gdzie rośnie bokkonia?
    sentences:
      - gdzie występuje rogownica szerokolistna?
      - Dłutowanie metodą Maaga Struganie metodą Sunderlanda
      - kim byli beatyfikowani przez papieża Jana Pawła II męczennicy z Almerii?
  - source_sentence: kto walczył o Brisbane?
    sentences:
      - Szczurza gorączka TAM Gorączka od ugryzienia szczura
      - Szczurza gorączka TAM Gorączka od ugryzienia szczura
      - który nadworny fotograf sprzedał swój patent firmie Eastman Kodak?
  - source_sentence: Morskie Oko (kabaret)
    sentences:
      - jak skończył się spór o Morskie Oko?
      - ile razy Srebrna Biblia była przywożona do Szwecji?
      - W latach 1955–1956 część więźniów przebywających w Spassku zwolniono.
  - source_sentence: ile katod ma duodioda?
    sentences:
      - kto nosi mantyle?
      - w jakim celu nowożeńcom w Korei wręcza się injeolmi?
      - W latach 1955–1956 część więźniów przebywających w Spassku zwolniono.
model-index:
  - name: bge-base-en-v1.5-klej-dyk
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.20432692307692307
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5024038461538461
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6802884615384616
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7548076923076923
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.20432692307692307
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1674679487179487
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1360576923076923
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07548076923076923
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.20432692307692307
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5024038461538461
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6802884615384616
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7548076923076923
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4741957684261531
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3839495573870572
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3909524912840153
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.19471153846153846
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.49278846153846156
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6634615384615384
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7548076923076923
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.19471153846153846
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1642628205128205
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.13269230769230766
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07548076923076921
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.19471153846153846
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.49278846153846156
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6634615384615384
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7548076923076923
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4648228460121699
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.37225847069597073
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.378344181427981
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.18990384615384615
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4543269230769231
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6057692307692307
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7067307692307693
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18990384615384615
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15144230769230768
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12115384615384615
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07067307692307692
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18990384615384615
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4543269230769231
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6057692307692307
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7067307692307693
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.437691661658994
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3522741147741148
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.35902651881139014
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.18509615384615385
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4375
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5480769230769231
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6442307692307693
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18509615384615385
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.14583333333333331
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1096153846153846
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06442307692307692
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18509615384615385
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4375
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5480769230769231
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6442307692307693
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4084493303372093
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.33323508089133086
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3393128348021269
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.17307692307692307
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3389423076923077
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4254807692307692
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5144230769230769
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17307692307692307
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11298076923076923
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08509615384615386
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05144230769230769
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17307692307692307
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3389423076923077
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.4254807692307692
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5144230769230769
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.333723313431585
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2768763354700855
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2853193687152632
            name: Cosine Map@100

bge-base-en-v1.5-klej-dyk

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Language: en
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(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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})
  (2): 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'ile katod ma duodioda?',
    'kto nosi mantyle?',
    'w jakim celu nowożeńcom w Korei wręcza się injeolmi?',
]
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

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.2043
cosine_accuracy@3	0.5024
cosine_accuracy@5	0.6803
cosine_accuracy@10	0.7548
cosine_precision@1	0.2043
cosine_precision@3	0.1675
cosine_precision@5	0.1361
cosine_precision@10	0.0755
cosine_recall@1	0.2043
cosine_recall@3	0.5024
cosine_recall@5	0.6803
cosine_recall@10	0.7548
cosine_ndcg@10	0.4742
cosine_mrr@10	0.3839
cosine_map@100	0.391

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1947
cosine_accuracy@3	0.4928
cosine_accuracy@5	0.6635
cosine_accuracy@10	0.7548
cosine_precision@1	0.1947
cosine_precision@3	0.1643
cosine_precision@5	0.1327
cosine_precision@10	0.0755
cosine_recall@1	0.1947
cosine_recall@3	0.4928
cosine_recall@5	0.6635
cosine_recall@10	0.7548
cosine_ndcg@10	0.4648
cosine_mrr@10	0.3723
cosine_map@100	0.3783

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1899
cosine_accuracy@3	0.4543
cosine_accuracy@5	0.6058
cosine_accuracy@10	0.7067
cosine_precision@1	0.1899
cosine_precision@3	0.1514
cosine_precision@5	0.1212
cosine_precision@10	0.0707
cosine_recall@1	0.1899
cosine_recall@3	0.4543
cosine_recall@5	0.6058
cosine_recall@10	0.7067
cosine_ndcg@10	0.4377
cosine_mrr@10	0.3523
cosine_map@100	0.359

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1851
cosine_accuracy@3	0.4375
cosine_accuracy@5	0.5481
cosine_accuracy@10	0.6442
cosine_precision@1	0.1851
cosine_precision@3	0.1458
cosine_precision@5	0.1096
cosine_precision@10	0.0644
cosine_recall@1	0.1851
cosine_recall@3	0.4375
cosine_recall@5	0.5481
cosine_recall@10	0.6442
cosine_ndcg@10	0.4084
cosine_mrr@10	0.3332
cosine_map@100	0.3393

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1731
cosine_accuracy@3	0.3389
cosine_accuracy@5	0.4255
cosine_accuracy@10	0.5144
cosine_precision@1	0.1731
cosine_precision@3	0.113
cosine_precision@5	0.0851
cosine_precision@10	0.0514
cosine_recall@1	0.1731
cosine_recall@3	0.3389
cosine_recall@5	0.4255
cosine_recall@10	0.5144
cosine_ndcg@10	0.3337
cosine_mrr@10	0.2769
cosine_map@100	0.2853

Training Details

Training Dataset

Unnamed Dataset

Size: 3,738 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 6 tokens
mean: 89.95 tokens
max: 512 tokens

min: 9 tokens
mean: 30.73 tokens
max: 76 tokens

	positive	anchor
type	string	string
details	min: 6 tokens mean: 89.95 tokens max: 512 tokens	min: 9 tokens mean: 30.73 tokens max: 76 tokens

Samples:

positive	anchor
`Rynek Kolumna Matki Boskiej, tzw. Kolumna Maryjna wykonana w latach 1725-1727 przez Johanna Melchiora Österreicha.`	`kto jest autorem kolumny maryjnej na raciborskim rynku?`
`Chleb razowy jest ciemniejszy i zawiera większą ilość błonnika oraz składników mineralnych niż chleb biały (pytlowy, czyli wypiekany z mąki przesiewanej przez pytel), bowiem jest w nim większy udział drobin pochodzących z łupin ziarna, gdzie gromadzą się te składniki.`	`które składniki razowego chleba odpowiadają za jego walory zdrowotne?`
`Najgłębsza znana studnia krasowa to jaskinia Vrtoglavica w Słowenii o głębokości ponad 600 metrów.`	`ile metrów głębokości mierzy studnia na podwórzu klasztoru w Czernej?`

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

eval_strategy: epoch
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
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: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
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: 4
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: True
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}
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: 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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.6838	10	6.5594	-	-	-	-	-
0.9573	14	-	0.3319	0.3751	0.3955	0.2618	0.4033
1.3675	20	4.2206	-	-	-	-	-
1.9829	29	-	0.3324	0.3591	0.3807	0.2833	0.3946
2.0513	30	3.3414	-	-	-	-	-
2.7350	40	2.9757	-	-	-	-	-
2.9402	43	-	0.3375	0.3570	0.3805	0.2840	0.3905
3.4188	50	2.8884	-	-	-	-	-
3.8291	56	-	0.3393	0.359	0.3783	0.2853	0.391

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.2
Sentence Transformers: 3.0.0
Transformers: 4.41.2
PyTorch: 2.3.1
Accelerate: 0.27.2
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}
}

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}
}