SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. 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: BAAI/bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

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: XLMRobertaModel 
  (1): 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})
)

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("BlackBeenie/bge-m3-msmarco-v3-sbert")
# Run inference
sentences = [
    'who is christopher kyle',
    'Chris Kyle American Sniper. Christopher Scott Kyle was born and raised in Texas and was a United States Navy SEAL from 1999 to 2009. He is currently known as the most successful sniper in American military history. According to his book American Sniper, he had 160 confirmed kills (which was from 255 claimed kills).',
    "'American Sniper' Chris Kyle's wife thanks audiences for 'watching the hard stuff'. Taya Kyle has told of her gratitude to audiences for supporting the film about her dead husband Chris Kyle, a Navy Seal played by Bradley Cooper.",
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 498,970 training samples
Columns: sentence_0, sentence_1, and sentence_2

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	sentence_2
type	string	string	string
details	min: 4 tokens mean: 9.93 tokens max: 37 tokens	min: 17 tokens mean: 90.01 tokens max: 239 tokens	min: 16 tokens mean: 86.47 tokens max: 229 tokens

Samples:

sentence_0	sentence_1	sentence_2
`how much does it cost to paint a interior house`	Interior House Painting Cost Factors. Generally, it will take a minimum of two gallons of paint to cover a room. At the highest end, paint will cost anywhere between $30 and $60 per gallon and come in three different finishes: flat, semi-gloss or high-gloss.Flat finishes are the least shiny and are best suited for areas requiring frequent cleaning.rovide a few details about your project and receive competitive quotes from local pros. The average national cost to paint a home interior is $1,671, with most homeowners spending between $966 and $2,426.	`Question DetailsAsked on 3/12/2014. Guest_... How much does it cost per square foot to paint the interior of a house? We just bought roughly a 1500 sg ft townhouse and want to get the entire house, including ceilings painted (including a roughly 400 sq ft finished basement not included in square footage).`
`when is s corp taxes due`	`If you form a corporate entity for your small business, regardless of whether it's taxed as a C or S corporation, a tax return must be filed with the Internal Revenue Service on its due date each year. Corporate tax returns are always due on the 15th day of the third month following the close of the tax year. The actual day that the tax return filing deadline falls on, however, isn't the same for every corporation.`	`But if you havenât, donât panic: the majority of forms arenât due quite yet. Most tax forms have an annual January 31 due date. Your tax forms are considered on time if the form is properly addressed and mailed on or before that date. If the regular due date falls on a Saturday, Sunday, or legal holiday â which is the case in 2015 for both January and February due dates â issuers have until the next business day.`
`what are disaccharides`	Disaccharides are formed when two monosaccharides are joined together and a molecule of water is removed, a process known as dehydration reaction. For example; milk sugar (lactose) is made from glucose and galactose whereas the sugar from sugar cane and sugar beets (sucrose) is made from glucose and fructose.altose, another notable disaccharide, is made up of two glucose molecules. The two monosaccharides are bonded via a dehydration reaction (also called a condensation reaction or dehydration synthesis) that leads to the loss of a molecule of water and formation of a glycosidic bond.	`Other disaccharides include (diagrams p. 364): Sucrose, common table sugar, has a glycosidic bond linking the anomeric hydroxyls of glucose and fructose. Because the configuration at the anomeric carbon of glucose is a (O points down from the ring), the linkage is designated a(12).`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 5
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: True
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: 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
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
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Click to expand

Epoch	Step	Training Loss
0.0321	500	0.3086
0.0641	1000	0.2339
0.0962	1500	0.2289
0.1283	2000	0.2262
0.1603	2500	0.2213
0.1924	3000	0.2158
0.2245	3500	0.2101
0.2565	4000	0.2082
0.2886	4500	0.2107
0.3207	5000	0.2015
0.3527	5500	0.2023
0.3848	6000	0.201
0.4169	6500	0.1974
0.4489	7000	0.191
0.4810	7500	0.1956
0.5131	8000	0.2
0.5451	8500	0.191
0.5772	9000	0.1888
0.6092	9500	0.1885
0.6413	10000	0.1936
0.6734	10500	0.1944
0.7054	11000	0.1806
0.7375	11500	0.1834
0.7696	12000	0.1853
0.8016	12500	0.1823
0.8337	13000	0.1827
0.8658	13500	0.1821
0.8978	14000	0.1724
0.9299	14500	0.1745
0.9620	15000	0.1776
0.9940	15500	0.1781
1.0	15593	-
1.0261	16000	0.1133
1.0582	16500	0.0964
1.0902	17000	0.0931
1.1223	17500	0.0947
1.1544	18000	0.097
1.1864	18500	0.0977
1.2185	19000	0.096
1.2506	19500	0.1005
1.2826	20000	0.1008
1.3147	20500	0.0998
1.3468	21000	0.0972
1.3788	21500	0.0992
1.4109	22000	0.0994
1.4430	22500	0.1029
1.4750	23000	0.1008
1.5071	23500	0.0985
1.5392	24000	0.1013
1.5712	24500	0.1027
1.6033	25000	0.0988
1.6353	25500	0.0982
1.6674	26000	0.0994
1.6995	26500	0.0998
1.7315	27000	0.0989
1.7636	27500	0.101
1.7957	28000	0.099
1.8277	28500	0.096
1.8598	29000	0.0989
1.8919	29500	0.1011
1.9239	30000	0.0974
1.9560	30500	0.0999
1.9881	31000	0.0976
2.0	31186	-
2.0201	31500	0.0681
2.0522	32000	0.0478
2.0843	32500	0.0483
2.1163	33000	0.0485
2.1484	33500	0.0472
2.1805	34000	0.0482
2.2125	34500	0.0491
2.2446	35000	0.0484
2.2767	35500	0.0493
2.3087	36000	0.0484
2.3408	36500	0.0503
2.3729	37000	0.0498
2.4049	37500	0.0507
2.4370	38000	0.0502
2.4691	38500	0.0508
2.5011	39000	0.0483
2.5332	39500	0.0486
2.5653	40000	0.0494
2.5973	40500	0.0511
2.6294	41000	0.0508
2.6615	41500	0.0496
2.6935	42000	0.0487
2.7256	42500	0.0497
2.7576	43000	0.0491
2.7897	43500	0.0486
2.8218	44000	0.0503
2.8538	44500	0.0504
2.8859	45000	0.0499
2.9180	45500	0.048
2.9500	46000	0.047
2.9821	46500	0.0497
3.0	46779	-
3.0142	47000	0.0395
3.0462	47500	0.0247
3.0783	48000	0.0256
3.1104	48500	0.0254
3.1424	49000	0.0247
3.1745	49500	0.0251
3.2066	50000	0.0253
3.2386	50500	0.0263
3.2707	51000	0.0261
3.3028	51500	0.0259
3.3348	52000	0.0256
3.3669	52500	0.0254
3.3990	53000	0.026
3.4310	53500	0.0255
3.4631	54000	0.0255
3.4952	54500	0.0257
3.5272	55000	0.0249
3.5593	55500	0.0251
3.5914	56000	0.026
3.6234	56500	0.0246
3.6555	57000	0.0258
3.6876	57500	0.0266
3.7196	58000	0.0242
3.7517	58500	0.0251
3.7837	59000	0.0243
3.8158	59500	0.0249
3.8479	60000	0.0252
3.8799	60500	0.0251
3.9120	61000	0.025
3.9441	61500	0.0249
3.9761	62000	0.0254
4.0	62372	-
4.0082	62500	0.0221
4.0403	63000	0.0146
4.0723	63500	0.0146
4.1044	64000	0.0152
4.1365	64500	0.0153
4.1685	65000	0.0144
4.2006	65500	0.0154
4.2327	66000	0.0137
4.2647	66500	0.0145
4.2968	67000	0.0148
4.3289	67500	0.0148
4.3609	68000	0.0142
4.3930	68500	0.0148
4.4251	69000	0.0155
4.4571	69500	0.0148
4.4892	70000	0.0144
4.5213	70500	0.0144
4.5533	71000	0.0148
4.5854	71500	0.015
4.6175	72000	0.0149
4.6495	72500	0.0135
4.6816	73000	0.0142
4.7137	73500	0.0152
4.7457	74000	0.0144
4.7778	74500	0.0143
4.8099	75000	0.0141
4.8419	75500	0.0146
4.8740	76000	0.0142
4.9060	76500	0.0142
4.9381	77000	0.0147
4.9702	77500	0.0145
5.0	77965	-

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
Datasets: 3.3.2
Tokenizers: 0.21.0

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",
}

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}
}