SentenceTransformer based on BAAI/bge-base-en-v1.5

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 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': 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 = [
    'Movies about the dark side of Hollywood fame and power abuse',
    "Title: Frances\nGenres: Drama\nOverview: The true story of Frances Farmer's meteoric rise to fame in Hollywood and the tragic turn her life took when she was blacklisted.\nTagline: Her story is shocking, disturbing, compelling... and true.\nDirector: Graeme Clifford\nStars: Jessica Lange, Sam Shepard, Kim Stanley\nRelease Date: 1982-12-03\nKeywords: strong woman, falsely accused, insanity, movie business, feminism, biography, based on true story, evil mother, psychiatric hospital, female protagonist, hollywood, wrongful imprisonment, lost love, wrongful arrest, wrongful conviction, wrong diagnosis, lobotomy, frances farmer, power abuse, mother daughter relationship",
    "Title: Come Drink with Me\nGenres: Action, Adventure\nOverview: Golden Swallow is a fighter-for-hire who has been contracted by the local government to retrieve the governor's kidnapped son. Holding him is a group of rebels who are demanding that their leader be released from prison in return for the captured son. After a brief encounter with the gang at a local restaurant, Golden Swallow is joined by an inebriated wanderer Drunken Cat who aids her in her mission.\nTagline: \nDirector: King Hu\nStars: Cheng Pei-Pei, Elliot Ngok Wah, Chen Hung-Lieh\nRelease Date: 1966-04-07\nKeywords: kung fu, hero, showdown, kidnapping, warrior woman, gore, fistfight, forest, waterfall, murder, tough girl, monastery, heroine, inn, severed hand, wuxia, kung fu master, inner strength, beggar clan, tavern fight",
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 32,382 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: 8 tokens mean: 16.52 tokens max: 38 tokens	min: 37 tokens mean: 151.92 tokens max: 330 tokens	min: 48 tokens mean: 146.76 tokens max: 301 tokens

Samples:

sentence_0	sentence_1	sentence_2
`Something like a drama story dealing with disturbed teenager or life`	`Title: I Never Promised You a Rose Garden Genres: Drama Overview: A disturbed and institutionalized 16-year-old girl struggles between fantasy and reality. Tagline: When she tried to kill herself, it was just the beginning. Director: Anthony Page Stars: Kathleen Quinlan, Bibi Andersson, Ben Piazza Release Date: 1977-07-14 Keywords: disturbed teenager`	Title: Event Horizon Genres: Horror, Science Fiction, Mystery Overview: In 2047, a group of astronauts are sent to investigate and salvage the starship Event Horizon which disappeared mysteriously seven years before on its maiden voyage. However, it soon becomes evident that something sinister resides in its corridors. Tagline: Infinite space. Infinite terror. Director: Paul W. S. Anderson Stars: Laurence Fishburne, Sam Neill, Kathleen Quinlan Release Date: 1997-08-15 Keywords: space marine, nightmare, insanity, delusion, hallucination, space travel, cryogenics, gore, black hole, crew, flashback, evil spirit, alternate dimension, hellgate, religion, explosion, burning man, rescue team, super power, trapped in space, distress signal, 2040s, spaceship
`Stories of brave musketeers fighting against powerful adversaries for justice and love`	Title: The Three Musketeers Genres: Action, Adventure, Romance, Family Overview: The young D'Artagnan arrives in Paris with dreams of becoming a King's musketeer. He meets and quarrels with three men, Athos, Porthos, and Aramis, each of whom challenges him to a duel. D'Artagnan finds out they are musketeers and is invited to join them in their efforts to oppose Cardinal Richelieu, who wishes to increase his already considerable power over the King. D'Artagnan must also juggle affairs with the charming Constance Bonancieux and the passionate Lady De Winter, a secret agent for the Cardinal. Tagline: . . . One for All and All for Fun! Director: Richard Lester Stars: Michael York, Oliver Reed, Richard Chamberlain Release Date: 1973-12-11 Keywords: france, paris, france, based on novel or book, swordplay, fight, satire, dressmaker, louis xiii, sword fight, swordsman, musketeer, extramarital affair, swashbuckler, diamond theft, sword duel, diamond necklace, cardinal, 17th century, queen jewe...	Title: The Brood Genres: Horror, Science Fiction Overview: A man tries to uncover an unconventional psychologist's therapy techniques on his institutionalized wife, while a series of brutal attacks committed by a brood of mutant children coincides with the husband's investigation. Tagline: The Ultimate Experience in Inner Terror. Director: David Cronenberg Stars: Oliver Reed, Samantha Eggar, Art Hindle Release Date: 1979-05-25 Keywords: toronto, canada, mutant, transformation, psychologist, divorce, psychotherapist, canuxploitation
`Critically acclaimed drama films directed by Sarah Polley exploring the themes of illiteracy and based on novel or book`	Title: Women Talking Genres: Drama Overview: A group of women in an isolated religious colony struggle to reconcile their faith with a series of sexual assaults committed by the colony's men. Tagline: Do nothing. Stay and fight. Leave. Director: Sarah Polley Stars: Rooney Mara, Claire Foy, Jessie Buckley Release Date: 2022-12-23 Keywords: rape, based on novel or book, faith, illiteracy, bolivia, mennonites, religion, gang rape, teenage rape, meeting, duringcreditsstinger, woman director, sexual assault, abusive husband, 2000s, pregnancy from rape	Title: Alice in Wonderland Genres: Family, Fantasy, Adventure Overview: Alice, now 19 years old, returns to the whimsical world she first entered as a child and embarks on a journey to discover her true destiny. Tagline: You're invited to a very important date. Director: Tim Burton Stars: Mia Wasikowska, Johnny Depp, Anne Hathaway Release Date: 2010-03-03 Keywords: based on novel or book, queen, psychotic, fantasy world, taunting, live action remake, based on young adult novel, mischievous, absurd, dramatic, incredulous, amused, euphoric

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 4
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
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: 4
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: 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}
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
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: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.4941	500	0.796
0.9881	1000	0.517
1.4822	1500	0.3748
1.9763	2000	0.3682
2.4704	2500	0.2839
2.9644	3000	0.2849
3.4585	3500	0.2392
3.9526	4000	0.2373

Framework Versions

Python: 3.11.12
Sentence Transformers: 3.4.1
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.5.1
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",
}

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}
}

JJTsao
/

fine-tuned_movie_retriever-bge-base-en-v1.5-nl