Add files using upload-large-folder tool

0c4279e verified 4 months ago

15 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:42272
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-large-en-v1.5
widget:
  - source_sentence: Pegasus standing right
    sentences:
      - Concordia standing with cornucopia and branch, head facing right.
      - Pegasus walking right
      - Victory advancing left, holding wreath and palm-branch.
  - source_sentence: >-
      Felicitas seated left, holding caduceus in right hand and cornucopia
      cradled in left arm, SMT in exergue
    sentences:
      - >-
        Providentia draped standing facing, looking left, holding a globe in the
        right hand and a transverse sceptre in the left.
      - Victory walking left, holding a palm and a crown.
      - >-
        Genius standing left, holding patera and cornucopia; two stars in left
        field; crescent over Z in right; ANT in exergue.
  - source_sentence: Armored bust of Mars with helmet to the right, seen from the front.
    sentences:
      - >-
        Emperor in field dress with Victoria on globe and labarum standing to
        the right, left foot on a lying, bound prisoner.
      - >-
        Roma, helmeted and draped, standing left, holding a globe topped with a
        phoenix in the right hand and a transverse sceptre in the left; behind,
        a shield.
      - Eagle standing facing with wings spread, head left
  - source_sentence: Prow of galley right
    sentences:
      - Salus seated left, feeding from patera a serpent rising from altar.
      - >-
        The Dea Caelestis riding right on a lion, holding a drum in right hand
        and scepter in left; below, water gushing from rock with inscription IN
        CARTH.
      - Galley sailing to the left with rowers.
  - source_sentence: Providentia standing left, holding globe and cornucopiae
    sentences:
      - Fides Milites seated left
      - >-
        Jupiter to the left and Hercules to the right, standing face to face
        shaking hands; Jupiter holds a long spear in his left hand with cloak
        flowing over his right shoulder; Hercules holds his club in his left
        hand around which the lion skin is wrapped.
      - >-
        Sol in quadriga left, holding globe and whip, raising right hand, R
        thunderbolt Γ in ex.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

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

This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5. 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-large-en-v1.5
Maximum Sequence Length: 512 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': 512, 'do_lower_case': True, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 1024, '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 = [
    'Providentia standing left, holding globe and cornucopiae',
    'Fides Milites seated left',
    'Jupiter to the left and Hercules to the right, standing face to face shaking hands; Jupiter holds a long spear in his left hand with cloak flowing over his right shoulder; Hercules holds his club in his left hand around which the lion skin is wrapped.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.3315, 0.3332],
#         [0.3315, 1.0000, 0.3473],
#         [0.3332, 0.3473, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 42,272 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 3 tokens
mean: 20.12 tokens
max: 76 tokens

min: 3 tokens
mean: 19.79 tokens
max: 75 tokens

	sentence_0	sentence_1
type	string	string
details	min: 3 tokens mean: 20.12 tokens max: 76 tokens	min: 3 tokens mean: 19.79 tokens max: 75 tokens

Samples:

sentence_0	sentence_1
`Felicitas standing to the left holding a caduceus and cornucopia.`	`Felicitas standing with caduceus and cornucopia.`
`S P Q R/OB/C S in three lines within oak wreath`	`Legend in three lines within oak wreath`
`Iustitia seated to the left holding patera and scepter`	`Iustitia seated to the left holding patera and scepter.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
max_steps: 2642
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: 16
per_device_eval_batch_size: 16
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: 1
max_steps: 2642
lr_scheduler_type: linear
lr_scheduler_kwargs: None
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
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}
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}
parallelism_config: 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
project: huggingface
trackio_space_id: trackio
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
hub_revision: None
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: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0189	50	-
0.0379	100	-
0.0568	150	-
0.0757	200	-
0.0946	250	-
0.1136	300	-
0.1325	350	-
0.1514	400	-
0.1703	450	-
0.1893	500	1.0463
0.2082	550	-
0.2271	600	-
0.2460	650	-
0.2650	700	-
0.2839	750	-
0.3028	800	-
0.3217	850	-
0.3407	900	-
0.3596	950	-
0.3785	1000	0.9948
0.3974	1050	-
0.4164	1100	-
0.4353	1150	-
0.4542	1200	-
0.4731	1250	-
0.4921	1300	-
0.5110	1350	-
0.5299	1400	-
0.5488	1450	-
0.5678	1500	0.9288
0.5867	1550	-
0.6056	1600	-
0.6245	1650	-
0.6435	1700	-
0.6624	1750	-
0.6813	1800	-
0.7002	1850	-
0.7192	1900	-
0.7381	1950	-
0.7570	2000	0.9219
0.7759	2050	-
0.7949	2100	-
0.8138	2150	-
0.8327	2200	-
0.8516	2250	-
0.8706	2300	-
0.8895	2350	-
0.9084	2400	-
0.9273	2450	-
0.9463	2500	0.8954
0.9652	2550	-
0.9841	2600	-
1.0	2642	-

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.2.3
Transformers: 4.57.6
PyTorch: 2.10.0+cu128
Accelerate: 1.12.0
Datasets: 4.3.0
Tokenizers: 0.22.2

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}
}