metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:10K<n<100K
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-MiniLM-L12-v2
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: How does ZBo do it
    sentences:
      - That s how you do it RYU
      - Calum you need to follow me ok
      - fricken calum follow me im upset
  - source_sentence: Judi was a crazy mf
    sentences:
      - ZBo is a baaad man
      - quel surprise it s the Canucks
      - nope Id buy Candice s and I will
  - source_sentence: ZBo is a baaad man
    sentences:
      - Jeff Green is a BAAAAAAAAADDDDD man
      - Wow RIP Chris from Kriss Kross
      - Vick 32 and shady is 24
  - source_sentence: OH GOD SING IT VEDO
    sentences:
      - Wow wow wow Vedo just killed it
      - It s over on his facebook page
      - Why do I get amber alerts tho
  - source_sentence: ZBo is in top form
    sentences:
      - Miley Cyrus is over the top
      - Hiller flashing the leather eh
      - Im tryin to get to Chicago May 10th
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: semeval 15 dev
          type: semeval-15-dev
        metrics:
          - type: pearson_cosine
            value: 0.6231334838158124
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.5854181889364861
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.6182213570910924
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.583565039468049
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.6202960321095145
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.5854180844045054
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6231334928761973
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5854180353346093
            name: Spearman Dot
          - type: pearson_max
            value: 0.6231334928761973
            name: Pearson Max
          - type: spearman_max
            value: 0.5854181889364861
            name: Spearman Max

SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L12-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-L12-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 tokens
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': 128, 'do_lower_case': False}) with Transformer model: 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("marrodion/minilm-l12-v2-simple")
# Run inference
sentences = [
    'ZBo is in top form',
    'Miley Cyrus is over the top',
    'Hiller flashing the leather eh',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Dataset: semeval-15-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6231
spearman_cosine	0.5854
pearson_manhattan	0.6182
spearman_manhattan	0.5836
pearson_euclidean	0.6203
spearman_euclidean	0.5854
pearson_dot	0.6231
spearman_dot	0.5854
pearson_max	0.6231
spearman_max	0.5854

Training Details

Training Dataset

Unnamed Dataset

Size: 13,063 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 7 tokens
mean: 11.16 tokens
max: 28 tokens

min: 7 tokens
mean: 12.31 tokens
max: 22 tokens

min: 0.0
mean: 0.33
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 7 tokens mean: 11.16 tokens max: 28 tokens	min: 7 tokens mean: 12.31 tokens max: 22 tokens	min: 0.0 mean: 0.33 max: 1.0

Samples:

sentence1	sentence2	score
`EJ Manuel the 1st QB to go in this draft`	`But my bro from the 757 EJ Manuel is the 1st QB gone`	`1.0`
`EJ Manuel the 1st QB to go in this draft`	`Can believe EJ Manuel went as the 1st QB in the draft`	`1.0`
`EJ Manuel the 1st QB to go in this draft`	`EJ MANUEL IS THE 1ST QB what`	`0.6`

Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 4,727 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 7 tokens
mean: 10.04 tokens
max: 16 tokens

min: 7 tokens
mean: 12.22 tokens
max: 26 tokens

min: 0.0
mean: 0.33
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 7 tokens mean: 10.04 tokens max: 16 tokens	min: 7 tokens mean: 12.22 tokens max: 26 tokens	min: 0.0 mean: 0.33 max: 1.0

Samples:

sentence1	sentence2	score
`A Walk to Remember is the definition of true love`	`A Walk to Remember is on and Im in town and Im upset`	`0.2`
`A Walk to Remember is the definition of true love`	`A Walk to Remember is the cutest thing`	`0.6`
`A Walk to Remember is the definition of true love`	`A walk to remember is on ABC family youre welcome`	`0.2`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
warmup_ratio: 0.1
load_best_model_at_end: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_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: 1.0
num_train_epochs: 3.0
max_steps: -1
lr_scheduler_type: linear
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: 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: 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
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
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	semeval-15-dev_spearman_cosine
0.1837	300	0.0814	0.0718	0.5815
0.3674	600	0.0567	0.0758	0.5458
0.5511	900	0.0566	0.0759	0.5712
0.7348	1200	0.0499	0.0748	0.5751
0.9186	1500	0.0477	0.0771	0.5606
1.1023	1800	0.0391	0.0762	0.5605
1.2860	2100	0.0304	0.0738	0.5792
1.4697	2400	0.0293	0.0741	0.5757
1.6534	2700	0.0317	0.072	0.5967
1.8371	3000	0.029	0.0764	0.5640
2.0208	3300	0.0278	0.0757	0.5674
2.2045	3600	0.0186	0.0750	0.5723
2.3882	3900	0.0169	0.0719	0.5864
2.5720	4200	0.0177	0.0718	0.5905
2.7557	4500	0.0178	0.0719	0.5888
2.9394	4800	0.0165	0.0725	0.5854

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0
Accelerate: 0.30.1
Datasets: 2.19.1
Tokenizers: 0.19.1

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",
}