metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:10K<n<100K
  - loss:CoSENTLoss
base_model: sentence-transformers/all-MiniLM-L6-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: >-
      Driving or commuting to work feels draining, even if it's a short
      distance.
    sentences:
      - >-
        Symptoms during a manic episode include decreased need for sleep, more
        talkative than usual, flight of ideas, distractibility
      - >-
        I feel like I have lost a part of myself since the traumatic event, and
        I struggle to connect with others on a deeper level.
      - >-
        For at least 2 years, or 1 year in children and adolescents, numerous
        periods with hypomanic symptoms and depressive symptoms occur, neither
        meeting full criteria for hypomanic or major depressive episodes.
  - source_sentence: >-
      I felt like my thoughts were disconnected and chaotic during a manic
      episode.
    sentences:
      - >-
        Diagnosis requires one or more manic episodes, which may be preceded or
        followed by hypomanic or major depressive episodes.
      - >-
        I feel like I have lost a part of myself since the traumatic event, and
        I struggle to connect with others on a deeper level.
      - >-
        Depressed mood for most of the day, for more days than not, as indicated
        by subjective account or observation, for at least 2 years.
  - source_sentence: >-
      My insomnia has caused me to experience frequent headaches and muscle
      soreness.
    sentences:
      - Insomnia or hypersomnia nearly every day.
      - >-
        I have difficulty standing in long lines at the grocery store or the
        bank due to the fear of feeling trapped or overwhelmed.
      - >-
        For at least 2 years, or 1 year in children and adolescents, numerous
        periods with hypomanic symptoms and depressive symptoms occur, neither
        meeting full criteria for hypomanic or major depressive episodes.
  - source_sentence: >-
      The phobic object or situation almost always provokes immediate fear or
      anxiety.
    sentences:
      - The agoraphobic situations almost always provoke fear or anxiety.
      - >-
        I have difficulty standing in long lines at the grocery store or the
        bank due to the fear of feeling trapped or overwhelmed.
      - >-
        For at least 2 years, or 1 year in children and adolescents, numerous
        periods with hypomanic symptoms and depressive symptoms occur, neither
        meeting full criteria for hypomanic or major depressive episodes.
  - source_sentence: >-
      I engage in risky behaviors like reckless driving or reckless sexual
      encounters.
    sentences:
      - >-
        Symptoms during a manic episode include inflated self-esteem or
        grandiosity,increased goal-directed activity, or excessive involvement
        in risky activities.
      - >-
        Marked decrease in functioning in areas like work, interpersonal
        relations, or self-care since the onset of the disturbance.
      - >-
        The agoraphobic situations are actively avoided, require the presence of
        a companion, or are endured with intense fear or anxiety.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: FT label
          type: FT_label
        metrics:
          - type: pearson_cosine
            value: 0.40571243927086686
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.4157655660967662
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.4294377953337607
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.41636474785618866
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.4293067637823527
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.41576593946890283
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4057124337715868
            name: Pearson Dot
          - type: spearman_dot
            value: 0.4157663124606592
            name: Spearman Dot
          - type: pearson_max
            value: 0.4294377953337607
            name: Pearson Max
          - type: spearman_max
            value: 0.41636474785618866
            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("Hgkang00/FT-label-consent-10")
# Run inference
sentences = [
    'I engage in risky behaviors like reckless driving or reckless sexual encounters.',
    'Symptoms during a manic episode include inflated self-esteem or grandiosity,increased goal-directed activity, or excessive involvement in risky activities.',
    'Marked decrease in functioning in areas like work, interpersonal relations, or self-care since the onset of the disturbance.',
]
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: FT_label
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4057
spearman_cosine	0.4158
pearson_manhattan	0.4294
spearman_manhattan	0.4164
pearson_euclidean	0.4293
spearman_euclidean	0.4158
pearson_dot	0.4057
spearman_dot	0.4158
pearson_max	0.4294
spearman_max	0.4164

Training Details

Training Dataset

Unnamed Dataset

Size: 33,800 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 29 tokens
mean: 29.0 tokens
max: 29 tokens

min: 14 tokens
mean: 25.15 tokens
max: 43 tokens

min: 0.0
mean: 0.06
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 29 tokens mean: 29.0 tokens max: 29 tokens	min: 14 tokens mean: 25.15 tokens max: 43 tokens	min: 0.0 mean: 0.06 max: 1.0

Samples:

sentence1	sentence2	score
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`I often hear voices telling me things that are not real, even when I'm alone in my room.`	`1.0`
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`I have strong beliefs that people are plotting against me and trying to harm me, which makes it hard for me to trust anyone.`	`1.0`
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`Sometimes, I see things that others around me don't see, like strange figures or objects.`	`1.0`

Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 4,225 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 18 tokens
mean: 31.8 tokens
max: 60 tokens

min: 15 tokens
mean: 24.59 tokens
max: 41 tokens

min: 0.0
mean: 0.06
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 18 tokens mean: 31.8 tokens max: 60 tokens	min: 15 tokens mean: 24.59 tokens max: 41 tokens	min: 0.0 mean: 0.06 max: 1.0

Samples:

sentence1	sentence2	score
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`People around me have noticed that my behavior is becoming more erratic and unpredictable.`	`1.0`
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`There are times when I repeat certain actions or words without any clear purpose, almost like being stuck in a loop.`	`0.0`
`Presence of delusions, hallucinations or disorganized speech, for a significant portion of time within a 1-month period`	`I feel detached from reality at times and have trouble distinguishing between what is real and what is not.`	`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_train_batch_size: 256
per_device_eval_batch_size: 128
num_train_epochs: 10
warmup_ratio: 0.1

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 256
per_device_eval_batch_size: 128
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: 10
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: 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}
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	FT_label_spearman_cosine
0.0377	10	11.8816	-	-
0.0755	20	12.0633	-	-
0.1132	30	11.2972	-	-
0.1509	40	11.4435	-	-
0.1887	50	10.9872	-	-
0.2264	60	10.3121	-	-
0.2642	70	10.0711	-	-
0.3019	80	9.6888	-	-
0.3396	90	9.2037	-	-
0.3774	100	8.6158	-	-
0.4151	110	8.4605	-	-
0.4528	120	8.202	-	-
0.4906	130	7.9642	-	-
0.5283	140	7.8384	-	-
0.5660	150	7.8803	-	-
0.6038	160	7.419	-	-
1.0	133	8.435	8.1138	0.3813
2.0	266	7.7886	8.2494	0.4003
3.0	399	7.164	8.7060	0.4048
4.0	532	6.5921	9.5854	0.3882
5.0	665	6.2349	10.5716	0.4042
6.0	798	5.7831	10.9500	0.4147
7.0	931	5.4894	11.6387	0.4120
8.0	1064	5.2348	12.2129	0.4113
9.0	1197	5.0118	12.4632	0.4099
10.0	1330	4.8566	12.7203	0.4158

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0+cu121
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",
}

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},
}