metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:20
  - loss:CoSENTLoss
widget: []
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: validation
          type: validation
        metrics:
          - type: pearson_cosine
            value: -0.10073561135203735
            name: Pearson Cosine
          - type: spearman_cosine
            value: -0.05129891760425771
            name: Spearman Cosine
          - type: pearson_manhattan
            value: -0.07223520049199797
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: -0.05129891760425771
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: -0.056592337170460805
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: -0.05129891760425771
            name: Spearman Euclidean
          - type: pearson_dot
            value: -0.1007351930231386
            name: Pearson Dot
          - type: spearman_dot
            value: -0.05129891760425771
            name: Spearman Dot
          - type: pearson_max
            value: -0.056592337170460805
            name: Pearson Max
          - type: spearman_max
            value: -0.05129891760425771
            name: Spearman Max

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 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': 256, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'The weather is lovely today.',
    "It's so sunny outside!",
    'He drove to the stadium.',
]
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: validation
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	-0.1007
spearman_cosine	-0.0513
pearson_manhattan	-0.0722
spearman_manhattan	-0.0513
pearson_euclidean	-0.0566
spearman_euclidean	-0.0513
pearson_dot	-0.1007
spearman_dot	-0.0513
pearson_max	-0.0566
spearman_max	-0.0513

Training Details

Training Dataset

Unnamed Dataset

Size: 20 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 4 tokens
mean: 7.0 tokens
max: 12 tokens

min: 8 tokens
mean: 18.2 tokens
max: 31 tokens

min: 0.1
mean: 0.84
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 4 tokens mean: 7.0 tokens max: 12 tokens	min: 8 tokens mean: 18.2 tokens max: 31 tokens	min: 0.1 mean: 0.84 max: 1.0

Samples:

sentence1	sentence2	score
`search for anti slip shoes`	`Mens Shower Shoes With Holes Dry Quickly Bath Slippers Womens Non Slip Indoor Home Bedroom Pool Spa Guest College Dorm`	`0.8`
`men slim jeans`	`Urbano Fashion Mens Slim Fit Jeans`	`0.9`
`Looking for a red cotton shirt`	`Cotton Regular Fit Solid Red Shirt`	`1.0`

Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 5 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 4 tokens
mean: 5.6 tokens
max: 8 tokens

min: 8 tokens
mean: 17.8 tokens
max: 27 tokens

min: 0.0
mean: 0.54
max: 0.9

	sentence1	sentence2	score
type	string	string	float
details	min: 4 tokens mean: 5.6 tokens max: 8 tokens	min: 8 tokens mean: 17.8 tokens max: 27 tokens	min: 0.0 mean: 0.54 max: 0.9

Samples:

sentence1	sentence2	score
`sandal`	`Beslip Womens Mens Garden Clogs Shoes with Arch Support Unisex Comfort Slip-on Sandals`	`0.9`
`Looking for a men black jeans`	`DENNIE FOSTE Men Regular Mid Rise Black Jeans`	`0.9`
`comfortable running shoes`	`NYKD Everyday Stylish Running Sports Jacket with Pockets for Women`	`0.0`

Loss: CoSENTLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_eval_batch_size: 16
learning_rate: 3e-05
lr_scheduler_type: cosine
warmup_ratio: 0.1
load_best_model_at_end: True
ddp_find_unused_parameters: False

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 8
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
learning_rate: 3e-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
max_steps: -1
lr_scheduler_type: cosine
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: False
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
eval_on_start: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	validation_spearman_max
0.3333	1	5.5753	-	-
0.6667	2	3.8769	-	-
1.0	3	0.6162	9.5527	-0.0513
1.3333	4	0.9801	-	-
1.6667	5	1.1051	-	-
2.0	6	0.6455	9.1644	-0.0513

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.42.2
PyTorch: 2.3.0
Accelerate: 0.31.0
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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}