SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (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("DarkKnight001/sbert-extractive-cnn-dailymail")
# Run inference
sentences = [
    'The answer is simple, says Ben Judah, author of "Fragile Empire: How Russia Fell In and Out of Love with Vladimir Putin."',
    "Putin's approval rating has hovered in the mid 80s since last May .\nAnalysts differ in trying to explain the reason .",
    'Nancy Rica Schiff spent 10 years travelling around America tracking down professions that the rest of us never knew existed .\nWeird jobs include dog food eater, odour judge, and a semen collector .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.0986, -0.0304],
#         [ 0.0986,  1.0000,  0.0443],
#         [-0.0304,  0.0443,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 43,308 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 4 tokens
mean: 30.05 tokens
max: 119 tokens

min: 13 tokens
mean: 64.33 tokens
max: 232 tokens

min: 0.0
mean: 0.17
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 4 tokens mean: 30.05 tokens max: 119 tokens	min: 13 tokens mean: 64.33 tokens max: 232 tokens	min: 0.0 mean: 0.17 max: 1.0

Samples:

sentence_0	sentence_1	label
`The NSPCC has revealed that more than 5,000 under-18s have been questioned by the police over sex offences over the past three years .`	`Lib Dem peer warns that young women and girls are the 'main casualties' of an 'epidemic' of violent material found online . NSPCC found more than 5,000 under-18s have been questioned by the police over sex offences over the past three years .`	`0.6470588235294118`
`"If Qusayr falls at the hands of the regime, there is no way to stop the acts of reprisal, and that retribution will (reach) another level," rebel spokesman Col. Abdul Hamid Zakaria told the Al-Arabiya TV network last month.`	`More than 1,000 civilians are injured; many remain trapped, group says . Hezbollah in Syria is "blatant" violation of Lebanon's sovereignty, White House says . Some surprised by how U.S. wants more evidence on use of sarin gas, diplomat says . Rockets fall on Alawite communities in Homs .`	`0.0`
`to beautiful music that triggers important memories and that convey a .`	`University of Kent psychologists . investigated the moods of people listening to sad . music and asked them their reasons for picking the tracks . Depressed people prefer to listen to beautiful music that triggers important memories and that conveys a particular message . Johnny Cash, Leonard Cohen and Radiohead were popular choices of sad but beautiful music .`	`0.3384615384615384`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
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: 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: -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
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
0.1847	500	0.0282
0.3694	1000	0.0109
0.5541	1500	0.0099
0.7388	2000	0.0091
0.9235	2500	0.0089

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.1.2
Transformers: 4.57.1
PyTorch: 2.9.0+cu126
Accelerate: 1.11.0
Datasets: 4.0.0
Tokenizers: 0.22.1

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",
}

Downloads last month: 46

Safetensors

Model size

22.7M params

Tensor type

F32

Model tree for DarkKnight001/sbert-extractive-cnn-dailymail

Base model

sentence-transformers/all-MiniLM-L6-v2

Finetuned

(679)

this model