metadata

base_model: BAAI/bge-base-en-v1.5
language:
  - fr
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
  - generated_from_trainer
  - dataset_size:47560
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Qui a écouté le roi Asa et envoyé son armée contre les villes d'Israël?
    sentences:
      - Ben-Hadad.
      - Il se prosterna devant le roi, le visage contre terre.
      - Baescha, fils d'Achija.
  - source_sentence: >-
      Quelle est l'importance de distribuer tous ses biens aux pauvres sans
      charité?
    sentences:
      - Adina, fils de Schiza, était le chef des Rubénites.
      - Distribuer tous ses biens aux pauvres sans charité ne sert à rien.
      - L'Éternel.
  - source_sentence: Qui sont les enfants du père d'Étham?
    sentences:
      - Jizreel, Jischma, Jidbasch et leur sœur Hatselelponi.
      - Chaque division comptait vingt-quatre mille hommes.
      - >-
        Hosa était un fils de Merari et il avait quatre fils: Schimri, Hilkija,
        Thebalia, et Zacharie.
  - source_sentence: Combien de temps Nadab, fils de Jéroboam, a-t-il régné sur Israël?
    sentences:
      - >-
        Ils sont des serviteurs par le moyen desquels les frères ont cru, selon
        que le Seigneur l'a donné à chacun.
      - >-
        Sept fils: Jeusch, Benjamin, Éhud, Kenaana, Zéthan, Tarsis et
        Achischachar, enregistrés au nombre de dix-sept mille deux cents.
      - Deux ans.
  - source_sentence: >-
      Quand les Lévites devaient-ils se présenter pour louer et célébrer
      l'Éternel?
    sentences:
      - Chaque matin et chaque soir.
      - Cinq mille talents d'or et dix mille talents d'argent ont été donnés.
      - Il doit demeurer circoncis.
model-index:
  - name: BGE base bible test
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.13359388879019363
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.18795523183513946
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.21389234322259726
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.25102149582519095
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.13359388879019363
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.06265174394504648
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.04277846864451945
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0251021495825191
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.13359388879019363
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.18795523183513946
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.21389234322259726
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.25102149582519095
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.18816833747648484
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.16858798117458645
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.17400088915411802
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.12773139101083675
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.18546811156510926
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.20572037662106946
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.24213892343222598
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.12773139101083675
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.061822703855036416
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.041144075324213894
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0242138923432226
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.12773139101083675
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.18546811156510926
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.20572037662106946
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.24213892343222598
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.18151482198424093
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.1625760305898876
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.16802226648065993
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.12488896784508793
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.17463137324569195
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.19737075857168235
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.23272339669568307
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.12488896784508793
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.058210457748563975
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.03947415171433648
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.023272339669568307
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.12488896784508793
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.17463137324569195
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.19737075857168235
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.23272339669568307
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.17440736005896854
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.156282728049472
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.16141647615447188
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.10943329188132883
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.15686622845976195
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.17853970509859654
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.20838514833895896
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.10943329188132883
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.052288742819920644
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.03570794101971931
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0208385148338959
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.10943329188132883
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.15686622845976195
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.17853970509859654
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.20838514833895896
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.15566336146326976
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.13917031134121227
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.14405644027137798
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.08935867827322792
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.13181737431160065
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.15011547344110854
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.17694084206786284
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08935867827322792
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.04393912477053354
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.03002309468822171
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.01769408420678629
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08935867827322792
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.13181737431160065
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.15011547344110854
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.17694084206786284
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.13031373727839585
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.11575599150656894
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12066444582998255
            name: Cosine Map@100

BGE base bible test

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the json 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json
Language: fr
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("Steve77/bge-base-bible-retrieval")
# Run inference
sentences = [
    "Quand les Lévites devaient-ils se présenter pour louer et célébrer l'Éternel?",
    'Chaque matin et chaque soir.',
    "Cinq mille talents d'or et dix mille talents d'argent ont été donnés.",
]
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

Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.1336	0.1277	0.1249	0.1094	0.0894
cosine_accuracy@3	0.188	0.1855	0.1746	0.1569	0.1318
cosine_accuracy@5	0.2139	0.2057	0.1974	0.1785	0.1501
cosine_accuracy@10	0.251	0.2421	0.2327	0.2084	0.1769
cosine_precision@1	0.1336	0.1277	0.1249	0.1094	0.0894
cosine_precision@3	0.0627	0.0618	0.0582	0.0523	0.0439
cosine_precision@5	0.0428	0.0411	0.0395	0.0357	0.03
cosine_precision@10	0.0251	0.0242	0.0233	0.0208	0.0177
cosine_recall@1	0.1336	0.1277	0.1249	0.1094	0.0894
cosine_recall@3	0.188	0.1855	0.1746	0.1569	0.1318
cosine_recall@5	0.2139	0.2057	0.1974	0.1785	0.1501
cosine_recall@10	0.251	0.2421	0.2327	0.2084	0.1769
cosine_ndcg@10	0.1882	0.1815	0.1744	0.1557	0.1303
cosine_mrr@10	0.1686	0.1626	0.1563	0.1392	0.1158
cosine_map@100	0.174	0.168	0.1614	0.1441	0.1207

Training Details

Training Dataset

json

Dataset: json
Size: 47,560 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 8 tokens
mean: 21.23 tokens
max: 45 tokens

min: 3 tokens
mean: 25.14 tokens
max: 110 tokens
Samples:

anchor positive

Quels sont les noms des fils de Schobal? Aljan, Manahath, Ébal, Schephi et Onam

Quels sont les noms des fils de Tsibeon? Ajja et Ana

Qui est le fils d'Ana? Dischon

	anchor	positive
type	string	string
details	min: 8 tokens mean: 21.23 tokens max: 45 tokens	min: 3 tokens mean: 25.14 tokens max: 110 tokens

anchor	positive
`Quels sont les noms des fils de Schobal?`	`Aljan, Manahath, Ébal, Schephi et Onam`
`Quels sont les noms des fils de Tsibeon?`	`Ajja et Ana`
`Qui est le fils d'Ana?`	`Dischon`

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
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: 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
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: 3
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: 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: 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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	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
0.0538	10	12.8804	-	-	-	-	-
0.1076	20	12.4714	-	-	-	-	-
0.1615	30	11.8263	-	-	-	-	-
0.2153	40	11.014	-	-	-	-	-
0.2691	50	10.1609	-	-	-	-	-
0.3229	60	10.6807	-	-	-	-	-
0.3767	70	9.3215	-	-	-	-	-
0.4305	80	10.3719	-	-	-	-	-
0.4844	90	9.4147	-	-	-	-	-
0.5382	100	9.5567	-	-	-	-	-
0.5920	110	8.7699	-	-	-	-	-
0.6458	120	9.0428	-	-	-	-	-
0.6996	130	9.0977	-	-	-	-	-
0.7534	140	8.0843	-	-	-	-	-
0.8073	150	8.1363	-	-	-	-	-
0.8611	160	7.5306	-	-	-	-	-
0.9149	170	7.7972	-	-	-	-	-
0.9687	180	7.9644	-	-	-	-	-
0.9956	185	-	0.1917	0.1879	0.1784	0.1583	0.1268
1.0225	190	7.6124	-	-	-	-	-
1.0764	200	6.6315	-	-	-	-	-
1.1302	210	7.2313	-	-	-	-	-
1.1840	220	6.5394	-	-	-	-	-
1.2378	230	6.7843	-	-	-	-	-
1.2916	240	6.9276	-	-	-	-	-
1.3454	250	7.2281	-	-	-	-	-
1.3993	260	6.9158	-	-	-	-	-
1.4531	270	6.5158	-	-	-	-	-
1.5069	280	6.916	-	-	-	-	-
1.5607	290	6.5717	-	-	-	-	-
1.6145	300	6.9225	-	-	-	-	-
1.6683	310	7.3981	-	-	-	-	-
1.7222	320	6.894	-	-	-	-	-
1.7760	330	6.0293	-	-	-	-	-
1.8298	340	5.9389	-	-	-	-	-
1.8836	350	5.959	-	-	-	-	-
1.9374	360	6.4268	-	-	-	-	-
1.9913	370	6.7366	-	-	-	-	-
1.9966	371	-	0.2012	0.1965	0.1862	0.1633	0.1361
2.0451	380	5.7871	-	-	-	-	-
2.0989	390	5.7358	-	-	-	-	-
2.1527	400	6.0964	-	-	-	-	-
2.2065	410	5.8331	-	-	-	-	-
2.2603	420	5.6152	-	-	-	-	-
2.3142	430	6.5018	-	-	-	-	-
2.3680	440	5.9798	-	-	-	-	-
2.4218	450	6.0598	-	-	-	-	-
2.4756	460	5.8222	-	-	-	-	-
2.5294	470	6.303	-	-	-	-	-
2.5832	480	5.9648	-	-	-	-	-
2.6371	490	6.415	-	-	-	-	-
2.6909	500	7.084	-	-	-	-	-
2.7447	510	5.692	-	-	-	-	-
2.7985	520	5.7706	-	-	-	-	-
2.8523	530	5.6943	-	-	-	-	-
2.9062	540	5.6817	-	-	-	-	-
2.9600	550	6.1265	-	-	-	-	-
2.9869	555	-	0.1882	0.1815	0.1744	0.1557	0.1303

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.3.1
Transformers: 4.45.2
PyTorch: 2.5.1
Accelerate: 1.2.1
Datasets: 2.19.1
Tokenizers: 0.20.1

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}
}