Hgkang00/FT-label-aug-consent-10

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-aug-consent-10")
# Run inference
sentences = [
    'Insomnia has led me to experience frequent headaches and muscle soreness.',
    'My insomnia has caused me to experience frequent headaches and muscle soreness.',
    'I struggle with distinguishing between reality and illusions when I feel detached from reality at times.',
]
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_aug
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.4256
spearman_cosine	0.2325
pearson_manhattan	0.5095
spearman_manhattan	0.2319
pearson_euclidean	0.5154
spearman_euclidean	0.2325
pearson_dot	0.4256
spearman_dot	0.2325
pearson_max	0.5154
spearman_max	0.2325

Training Details

Training Dataset

Unnamed Dataset

• Size: 133,800 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 11 tokens mean: 31.63 tokens max: 63 tokens	min: 14 tokens mean: 25.22 tokens max: 41 tokens	min: -1.0 mean: -0.92 max: 1.0

• Samples:

  sentence1	sentence2	score
  Presence of one or more of the following intrusion symptoms associated with the traumatic event: recurrent distressing memories, dreams, flashbacks, psychological distress, or physiological reactions to cues of the traumatic event.	I avoid making phone calls, even to close friends or family, because I'm afraid of saying something wrong or sounding awkward.	0.0
  The phobic object or situation almost always provokes immediate fear or anxiety.	I find it hard to stick to a consistent eating schedule, sometimes going days without feeling the need to eat at all.	-1.0
  The fear or anxiety is out of proportion to the actual danger posed by the specific object or situation and to the sociocultural context.	I have difficulty going to places where I feel there are no immediate exits, such as cinemas or auditoriums, as the fear of being stuck or unable to escape escalates my anxiety.	-1.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 104,225 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 11 tokens mean: 31.24 tokens max: 63 tokens	min: 15 tokens mean: 24.86 tokens max: 41 tokens	min: -1.0 mean: -0.93 max: 1.0

• Samples:

  sentence1	sentence2	score
  Excessive anxiety and worry occurring more days than not for at least 6 months, about a number of events or activities such as work or school performance.	Simple activities like going for a walk or doing household chores feel like daunting tasks due to my low energy levels.	-1.0
  The individual fears acting in a way or showing anxiety symptoms that will be negatively evaluated, leading to humiliation, embarrassment, rejection, or offense to others.	I often find myself mindlessly snacking throughout the day due to changes in my appetite.	-1.0
  Persistent avoidance of stimuli associated with the trauma, evidenced by avoiding distressing memories, thoughts, or feelings, or external reminders of the event.	Simple activities like going for a walk or doing household chores feel like daunting tasks due to my low energy levels.	-1.0

• 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
• batch_sampler: no_duplicates

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: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	FT_label_aug_spearman_cosine
1.0	523	7.773	-	-
2.0	1046	0.0004	-	-
2.9828	1560	-	11.8818	0.2184
1.0172	1569	0.1169	-	-
2.0172	2092	5.4076	-	-
3.0172	2615	0.0002	-	-
3.9828	3120	-	11.8669	0.2054
2.0344	3138	0.1571	-	-
3.0344	3661	4.0179	-	-
4.0344	4184	0.0001	-	-
4.9828	4680	-	12.8814	0.2291
3.0516	4707	0.1592	-	-
4.0516	5230	2.835	13.5336	0.2325

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},
}