README.md

metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:560
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Let's search inside
    sentences:
      - Stuffed animal
      - Let's look inside
      - What is worse?
  - source_sentence: I want a torch
    sentences:
      - What do you think of Spike
      - Actually I want a torch
      - Why candle?
  - source_sentence: Magic trace
    sentences:
      - A sword.
      - ' Why is he so tiny?'
      - 'The flower is changed into flower. '
  - source_sentence: Did you use illusion?
    sentences:
      - Do you use illusion?
      - You are a cat?
      - It's Toby
  - source_sentence: Do you see your scarf in the watering can?
    sentences:
      - What is the Weeping Tree?
      - Are these your footprints?
      - Magic user
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: custom arc semantics data
          type: custom-arc-semantics-data
        metrics:
          - type: cosine_accuracy
            value: 0.85
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.49632835388183594
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.8727272727272727
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.48691314458847046
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.8888888888888888
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8571428571428571
            name: Cosine Recall
          - type: cosine_ap
            value: 0.927175101411552
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.85
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 0.4963283836841583
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.8727272727272727
            name: Dot F1
          - type: dot_f1_threshold
            value: 0.48691320419311523
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.8888888888888888
            name: Dot Precision
          - type: dot_recall
            value: 0.8571428571428571
            name: Dot Recall
          - type: dot_ap
            value: 0.927175101411552
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.8428571428571429
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 15.624195098876953
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.8681318681318683
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 18.23479461669922
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.8061224489795918
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.9404761904761905
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.9264219833665228
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.85
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 1.00364351272583
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.8727272727272727
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 1.0129987001419067
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.8888888888888888
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.8571428571428571
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.927175101411552
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.85
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 15.624195098876953
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.8727272727272727
            name: Max F1
          - type: max_f1_threshold
            value: 18.23479461669922
            name: Max F1 Threshold
          - type: max_precision
            value: 0.8888888888888888
            name: Max Precision
          - type: max_recall
            value: 0.9404761904761905
            name: Max Recall
          - type: max_ap
            value: 0.927175101411552
            name: Max Ap

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("LeoChiuu/all-MiniLM-L6-v2")
# Run inference
sentences = [
    'Do you see your scarf in the watering can?',
    'Are these your footprints?',
    'Magic user',
]
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

Binary Classification

• Dataset: custom-arc-semantics-data
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.85
cosine_accuracy_threshold	0.4963
cosine_f1	0.8727
cosine_f1_threshold	0.4869
cosine_precision	0.8889
cosine_recall	0.8571
cosine_ap	0.9272
dot_accuracy	0.85
dot_accuracy_threshold	0.4963
dot_f1	0.8727
dot_f1_threshold	0.4869
dot_precision	0.8889
dot_recall	0.8571
dot_ap	0.9272
manhattan_accuracy	0.8429
manhattan_accuracy_threshold	15.6242
manhattan_f1	0.8681
manhattan_f1_threshold	18.2348
manhattan_precision	0.8061
manhattan_recall	0.9405
manhattan_ap	0.9264
euclidean_accuracy	0.85
euclidean_accuracy_threshold	1.0036
euclidean_f1	0.8727
euclidean_f1_threshold	1.013
euclidean_precision	0.8889
euclidean_recall	0.8571
euclidean_ap	0.9272
max_accuracy	0.85
max_accuracy_threshold	15.6242
max_f1	0.8727
max_f1_threshold	18.2348
max_precision	0.8889
max_recall	0.9405
max_ap	0.9272

Training Details

Training Dataset

Unnamed Dataset

• Size: 560 training samples
• Columns: text1, text2, and label
• Approximate statistics based on the first 1000 samples:

  	text1	text2	label
  type	string	string	int
  details	min: 3 tokens mean: 7.2 tokens max: 18 tokens	min: 3 tokens mean: 7.26 tokens max: 18 tokens	0: ~36.07% 1: ~63.93%

• Samples:

  text1	text2	label
  When it was dinner	Dinner time	1
  Did you cook chicken noodle last night?	Did you make chicken noodle for dinner?	1
  Someone who can change item	Someone who uses magic that turns something into something.	1

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 140 evaluation samples
• Columns: text1, text2, and label
• Approximate statistics based on the first 1000 samples:

  	text1	text2	label
  type	string	string	int
  details	min: 3 tokens mean: 6.99 tokens max: 18 tokens	min: 3 tokens mean: 7.29 tokens max: 18 tokens	0: ~40.00% 1: ~60.00%

• Samples:

  text1	text2	label
  Let's check inside	Let's search inside	1
  Sohpie, are you okay?	Sophie Are you pressured?	0
  This wine glass is related.	This sword looks important.	0

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• learning_rate: 2e-05
• num_train_epochs: 13
• warmup_ratio: 0.1
• fp16: True
• 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: 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
• torch_empty_cache_steps: None
• learning_rate: 2e-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: 13
• 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: True
• 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
• eval_on_start: False
• eval_use_gather_object: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	custom-arc-semantics-data_max_ap
None	0	-	-	0.9254
1.0	70	1.1722	1.2175	0.9237
2.0	140	0.7774	1.0454	0.9291
3.0	210	0.4122	1.0024	0.9316
4.0	280	0.229	0.9819	0.9285
5.0	350	0.1509	0.9215	0.9321
6.0	420	0.0988	0.9119	0.9312
7.0	490	0.0772	0.8962	0.9303
8.0	560	0.0564	0.8905	0.9272
9.0	630	0.0449	0.8878	0.9266
10.0	700	0.037	0.8841	0.9273
11.0	770	0.0387	0.8881	0.9265
12.0	840	0.0332	0.8884	0.9274
13.0	910	0.032	0.8890	0.9272

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 3.0.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Accelerate: 0.34.2
• Datasets: 2.20.0
• 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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}